Digital Pathology Podcast

In this episode of the Digital Pathology Podcast, I sit down with Matthew Nuñez, CEO of MUSE Microscopy, to discuss the groundbreaking advancements in direct-to-digital imaging in pathology. Traditional pathology workflows rely on glass slides, formalin fixation, and time-consuming processing steps. But what if we could skip the slide entirely and go straight to digital?

🔬 Key Topics Covered:

[00:00:00] The Challenges of Traditional Pathology Workflows
[00:01:00] Introducing MUSE: The First Direct-to-Digital Pathology Imager
[00:02:00] How MUSE Captures Whole Tissue Images Without Slides
[00:04:00] The Science Behind Microscopy with UV Light Surface Excitation
[00:06:00] Eliminating Tissue Processing Delays with Real-Time Imaging
[00:08:00] How Direct-to-Digital Imaging Improves Speed & Diagnostic Accuracy
[00:10:00] Applications in Pathology: From Clinical Use to Organ Transplants
[00:12:00] How MUSE Supports Remote and Mobile Pathology Clinics
[00:15:00] Bridging the Gap Between Veterinary and Human Pathology
[00:18:00] The Future of Pathology: Faster Diagnoses, Better Patient Care

🩺 Why This Episode Matters:
Pathology is the gateway to diagnosis and patient care—but traditional workflows create delays, inefficiencies, and logistical challenges. With direct-to-digital imaging, we can eliminate glass slides, reduce errors, and enable real-time diagnostics. In this conversation, Matthew Nuñez explains how MUSE is transforming pathology by bringing AI-powered imaging directly to the tissue, skipping the slide, and making diagnoses faster than ever before.

🚀 What’s Next?
This disruptive technology is paving the way for on-site pathology, remote consultations, and real-time patient interaction. If you're attending USCAP 2025, make sure to visit the MUSE booth and witness direct-to-digital imaging in action.

📢 Can't attend in person? Join the USCAP 2025 online experience on March 24, 2025, from 5:30 to 7:00 PM EST!

REGISTER HERE

ℹ️ This Episode's Resources:

#DigitalPathology #AIinHealthcare #PathologyInnovation #DirectToDigital

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

126: How Can Digital Pathology Workflows Stay Compliant and Efficient w/ Scott Randall, Hamamatsu and and Amanda Coble, Proscia

17 mars 2025 | 40 min

How Can Digital Pathology Workflows Stay Compliant and Efficient?

In this episode of the Digital Pathology Podcast, I sit down with Scott Randall, Senior Application Specialist at Hamamatsu (Hamamatsu NanoZoomer), and Amanda Coble, Senior Director of Product for Proscia (Proscia’s Website), to discuss the critical role of compliance, interoperability, and efficiency in digital pathology workflows.

🔬 Key Topics Covered:

[00:00:00] Introduction and Initial Challenges in Digital Pathology Compliance
[00:01:00] Guest Introductions: Meet Scott and Amanda
[00:03:00] Hamamatsu’s FDA Clearance Journey: Lessons Learned
[00:06:00] Proscia’s Path to FDA Clearance and Partnering with Hamamatsu
[00:10:00] How Digital Pathology Systems Maintain Compliance
[00:14:00] The Advantages of Open Architecture in Digital Pathology
[00:18:00] Overcoming Challenges in Slide Scanning and Logistics
[00:22:00] Phases of Digital Pathology Adoption and Future-Proofing Labs
[00:27:00] The Role of AI and Automation in Digital Pathology Workflows
[00:32:00] Advice for Vendors Looking to Build Compliant Digital Pathology Solutions
[00:38:00] Final Thoughts: The Future of Interoperability and Compliance

🩺 Why This Episode Matters:
Regulatory approval in digital pathology isn’t just about scanning slides—it’s about building a seamless, interoperable workflow that ensures accuracy, efficiency, and compliance. Hamamatsu and Proscia were among the first companies to successfully achieve FDA clearance for their integrated solutions, setting the stage for future innovations in AI-powered digital pathology.

Episode Resources:

Learn more about Hamamatsu’s NanoZoomer series: Hamamatsu NanoZoomer
Discover Proscia’s AI-driven pathology software: Proscia’s Website
Read the DPP Blog on selecting the right whole-slide scanner: Choosing the Right Whole-Slide Scanner for Your Pathology Lab

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

125: Direct-to-Digital Tissue Imaging | Interview with Drs. Rao and Edwards, Muse Microscopy

9 mars 2025 | 21 min

124: Slide-free Digital Pathology | Deep Dive into Muse Microscopy

6 mars 2025 | 20 min

122: The Role of Generative vs. Non-Generative AI in Medical Diagnostics

5 mars 2025 | 77 min

In this episode of the Digital Pathology Podcast, I explore the evolving role of Generative vs. Non-Generative AI in Medical Diagnostics. As AI continues to transform the medical field, understanding the differences between these two approaches is essential for pathologists, researchers, and healthcare professionals.

We break down the key concepts behind generative AI models (like ChatGPT and image-generation tools) and non-generative AI models (such as traditional machine learning for diagnostic support). I also highlight a groundbreaking seven-part AI review series published in Modern Pathology, which serves as a crucial reference for integrating AI into pathology.

🔬 Key Topics Covered:

[00:00:00] Introduction and Technical Adjustments
[00:02:00] Why AI Education in Pathology Is More Important Than Ever
[00:04:00] Overview of the Modern Pathology AI Review Series
[00:06:00] Generative vs. Non-Generative AI: What’s the Difference?
[00:08:00] AI in Pathology: Current Applications and Future Potential
[00:12:00] Addressing Bias and Ethical Concerns in AI Models
[00:16:00] How AI Can Improve Accuracy in Medical Imaging
[00:20:00] The Role of Large Language Models (LLMs) in Pathology
[00:25:00] Multi-Modal AI: The Future of Integrating Imaging and Text Data
[00:30:00] Real-World Use Cases and AI-Driven Diagnostics

🩺 Why This Episode Matters:
AI is no longer a futuristic concept—it’s here, and it’s shaping the future of digital pathology and medical diagnostics. In this episode, I break down how AI can enhance accuracy, improve workflow efficiency, and make diagnostic insights more accessible. However, AI models also come with risks, such as bias and interpretability challenges, which we need to address responsibly.

🚀 Take Action:
AI in pathology isn’t just a passing trend—it’s a paradigm shift. Whether you're a pathologist, researcher, or lab professional, this episode will give you the knowledge you need to stay ahead in the era of AI-driven diagnostics.

🎧 Listen now and explore the future of AI in pathology!

👉 Watch it here: https://www.youtube.com/live/Mq4Xwxoq_ok?si=o7bA90BlZff9iI_A

#DigitalPathology #AIinHealthcare #PathologyInnovation #GenerativeAI

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

123: Generative AI: Deeper Dive

5 mars 2025 | 53 min

In this episode of the Digital Pathology Podcast, I take a deeper dive into Generative AI in Pathology, following the AI in Pathology series published by USCAP. AI has already begun transforming medical diagnostics, but what does Generative AI mean for digital pathology? From synthetic data generation to multimodal AI models, this episode explores the cutting edge of AI’s role in pathology and how it’s evolving to enhance efficiency, accuracy, and patient care.

🔬 Key Topics Covered:

[00:00:00] Introduction – The Evolution of AI in Pathology
[00:02:00] Acknowledging the Authors Behind the AI Review Series
[00:04:00] What Is Generative AI and Why Is It a Game-Changer?
[00:06:00] The Cambrian Explosion of Generative AI in Medicine
[00:08:00] Understanding Transformer Architectures and Cloud Computing
[00:12:00] ChatGPT, DALLE, and Multi-Modal AI: What’s Next?
[00:18:00] Synthetic Data Generation: A New Era for Pathology Training
[00:24:00] How AI Can Pass Medical Exams and Assist Pathologists
[00:30:00] Reducing Bias and Ethical Concerns in AI-Based Diagnostics
[00:38:00] Real-World Use Cases of AI-Generated Pathology Reports
[00:45:00] The Future of Generative AI in Digital Pathology

🩺 Why This Episode Matters:
Generative AI is no longer just a concept—it’s already being used to train models, generate high-fidelity pathology images, and assist with diagnostic decision-making. However, challenges remain, from bias in AI models to the need for domain-specific training data. Understanding these factors is essential for pathologists and medical professionals who want to leverage AI responsibly in clinical practice.

🚀 What’s Next?
This episode discusses not just what Generative AI is but how it can reshape pathology workflows and where we’re headed next. If you’re interested in how AI can improve efficiency and accuracy in diagnostics, this is a conversation you don’t want to miss.

🎧 Listen now to explore the future of Generative AI in pathology!

👉 Watch or listen here: https://www.youtube.com/live/hRv9GmMWSjk?si=OEg8gafqRA2M_zlx

#DigitalPathology #AIinHealthcare #PathologyInnovation #GenerativeAI

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

121: How Pathology Images Can Transform Cancer Understanding w/ Dr. Lija Joseph

3 februari 2025 | 54 min

In this episode of the Digital Pathology Podcast, I sit down with Dr. Lija Joseph, a pathologist who is redefining patient care by making pathology more accessible and understandable. Traditionally, pathology has been a “behind-the-scenes” specialty, but Dr. Joseph is changing that by directly engaging with patients, showing them their pathology slides, and empowering them with knowledge about their diagnoses.

🔬 Key Topics Covered:

[00:00:00] Introduction to Patient-Centric Pathology
[00:01:00] Meet Dr. Lija Joseph: Her Background and Journey
[00:05:00] The Patient Who Inspired a New Approach
[00:10:00] Why Patients Need to See Their Pathology Images
[00:15:00] The Power of Knowledge: How Patient Awareness Improves Care
[00:20:00] Overcoming Barriers to Patient-Pathologist Communication
[00:25:00] How Digital Pathology Can Make This Scalable
[00:30:00] The Role of Technology in Breaking Down Access Barriers
[00:35:00] Convincing Healthcare Leadership to Support This Initiative
[00:40:00] How Digital Pathology Can Transform Patient Outcomes

🩺 Why This Matters:
Most patients never meet their pathologists—but should they? Dr. Joseph believes so. She shares powerful stories of how patients who see their own slides gain a deeper understanding of their disease, make better treatment decisions, and experience greater peace of mind.

🚀 How Digital Pathology Can Change the Future:
Dr. Joseph’s approach is innovative, but digital pathology can take it even further. Imagine a world where patients don’t have to visit a hospital to see their biopsy results but can access them remotely through secure digital platforms. This technology has the potential to bridge the gap between patients and their pathologists, improving care and trust.

🎧 Tune in now to learn how pathology can become more patient-focused!

#DigitalPathology #PatientCenteredCare #PathologyInnovation #AIinHealthcare

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

120: DigPath Digest #21 | AI's Role in Prostate & Breast Cancer Diagnosis and Collaborative Annotation Tools

26 januari 2025 | 46 min

119: DigitPath Digest #19 | Cytology's Digital Revolution, Prostate Cancer Tsunami + Live AI Demo

11 januari 2025 | 32 min

118: Why are So Few Pathologists Attending Digital Pathology Conferences

11 december 2024 | 31 min

In this episode, I’m joined by Dr. Giovanni Lujan, Nick Best, and Dr. Alae Kawam to explore a topic that hits close to home for many of us in digital pathology: why do so few pathologists attend digital pathology conferences? We delve into the barriers, opportunities, and actionable solutions that can help bridge this gap and drive the adoption of digital pathology across the profession.

What You’ll Hear in This Episode:

Startling Observations (00:02:00): Only 10% of attendees at some digital pathology conferences are pathologists. Why is this the case, and what does it mean for the future of the field?
Barriers to Adoption (00:04:00): From time constraints to a lack of institutional support, we unpack the key challenges stopping pathologists from going digital.
Mentorship and Collaboration (00:09:00): How mentorship programs can connect seasoned professionals with early-career pathologists to share knowledge and drive adoption.
The Role of the Next Generation (00:15:00): Insights into how young pathologists can lead the way with their enthusiasm and fresh perspectives.
Engaging the Skeptics (00:07:00): Strategies to introduce hesitant or resistant pathologists to the transformative power of digital tools.
Global Comparisons (00:10:00): What can the U.S. learn from Europe and Asia about accelerating digital pathology adoption?
Leveraging Leadership and Advocacy (00:19:00): How young pathologists can work with leadership to introduce digital pathology as a standard practice in their organizations.
The Impact of Digital Pathology on Work-Life Balance (00:20:00): Exploring how remote sign-outs and shorter turnaround times can enhance both patient care and pathologists’ quality of life.
Making Digital Pathology the Norm (00:24:00): Ideas for shifting digital pathology from a secondary option to the standard of care, addressing common fears and misconceptions.
Future Plans and Next Steps (00:28:00): A look at actionable steps for advancing digital pathology through podcasts, mentorship, and departmental advocacy.

Key Takeaways:
This conversation isn’t just about identifying challenges—it’s about solutions. We discuss how collaboration, leadership, and individual responsibility can drive meaningful change in digital pathology. Whether you’re a seasoned pathologist or just starting your career, this episode offers inspiration and actionable ideas to make digital pathology a core part of the profession.

Connect With Us:
Share your thoughts on why more pathologists aren’t attending these conferences. What’s holding them back, and what changes would you like to see in your department? Let’s keep this important conversation going!

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

117: Tertiary Lymphoid Structures in Colorectal Cancer Prognosis | Dr. Aleks + AI

11 december 2024 | 22 min

Leveraging AI for Deep Insights into Tertiary Lymphoid Structures in Colorectal Cancer

In this episode of the Digital Pathology Podcast, I introduce 'Aleks + AI,' a new experimental series leveraging Google's Notebook LM to delve deeper into scientific literature.

Today's focus is on tertiary lymphoid structures (TLS) and their potential to predict colorectal cancer prognosis. We discuss a study published in the October 2024 issue of Precision Clinical Medicine, exploring different methods of quantifying TLS using digital pathology and AI.

The paper title is: "Comparative analysis of tertiary lymphoid structures for predicting survival of colorectal cancer: a whole-slide images-based study"

The findings highlight TLS density as a reliable predictor of survival and its correlation with immune responses and microsatellite instability. We also touch upon the potential for AI to streamline TLS analysis in clinical settings and the broader implications for personalized medicine. Join us as we dive into the intersection of digital pathology and computer science, featuring insights and commentary from my AI co-hosts, Hema and Toxy.

00:00 Welcome and Introduction
00:45 Introducing the New AI Tool: Notebook LM by Google
01:11 Experimental Series: "Aleks + AI"
02:06 Deep Dive into Tertiary Lymphoid Structures (TLS)
03:18 Understanding TLS and Their Role in Colorectal Cancer
04:20 Quantification Methods and Key Findings
05:02 Implications for Personalized Medicine
09:02 AI in TLS Analysis and Future Prospects
11:00 CMS Classification and TLS Density
12:08 Study Limitations and Future Directions
15:40 Final Thoughts and Wrap-Up
16:28 Feedback and Future Plans

THIS EPISODE'S RESOURCES

116: DigiPath Digest #18 | Federated Learning in Pathology. Developing AI Models While Preserving Privacy

PUBLICATION DISCUSSED TODAY

📝 Comparative analysis of tertiary lymphoid structures for predicting survival of colorectal cancer: a whole-slide images-based study
🔗https://academic.oup.com/pcm/article/7/4/pbae030/7826772

📱 Send us a text

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

116: DigiPath Digest #18 | Federated Learning in Pathology. Developing AI Models While Preserving Privacy

6 december 2024 | 27 min

115: Pathology Meets AI: Combining Veterinary and Medical Pathology for Digital Advancements w/ Richard Doughty, DVM, MD, MSc AIFORIA

3 december 2024 | 66 min

114: Radiology Partners’ approach to clinical AI applications: w/ Nina Kottler, MD, MS, FSIIM | Radiology Partners

15 november 2024 | 54 min

In this episode, I sit down with Dr. Nina Kottler, Associate Chief Medical Officer of Clinical AI at Radiology Partners, to dive into the evolving role of AI in radiology and how it can shape the future of digital pathology. Dr. Kottler shares her unique journey, expertise, and practical frameworks for implementing AI that enhance patient care and streamline diagnostic workflows.

Episode Highlights and Key Moments:

[00:00:45] Introduction to Dr. Nina Kottler
Dr. Kottler discusses her background in applied mathematics, her journey into medicine, and her work at Radiology Partners, where she combines clinical practice with AI innovation.
[00:04:30] Breaking Down Complex Problems in AI
Nina explains her approach to tackling large clinical challenges by breaking them down into manageable parts, a method that’s essential for developing and optimizing AI solutions.
[00:08:15] The Role of Data Orchestration
We dig into “data orchestration” and how ensuring data is aligned with the right AI model is key to producing accurate and reliable clinical outcomes.
[00:11:45] Life Cycle of an Exam in Radiology
Nina takes us through each step in the radiology workflow—from the initial patient consultation to reporting—and highlights how AI can streamline and enhance each phase.
[00:17:00] Evolution of AI Models in Healthcare
We explore how AI has evolved, from early CAD systems to today’s multimodal and transformer models, and the exciting possibilities they bring to both radiology and pathology.
[00:23:20] Addressing the Lag in AI Adoption in Healthcare
We discuss the challenge of keeping up with AI advancements while balancing patient safety, regulatory standards, and the need for reliability in clinical settings.
[00:27:50] Frameworks for Reducing Variability and Improving Accuracy
Nina shares actionable frameworks that Radiology Partners uses to reduce variability and improve diagnostic precision—strategies that pathology can learn from.
[00:32:40] AI in Workflow Optimization: Where It Has Real Impact
We discuss specific use cases in clinical workflows that show where AI can bring the greatest value, especially in enhancing patient care through optimized processes.
[00:36:50] The Power of Multimodal AI and Vision-Language Models
Combining large language models with computer vision is moving diagnostics closer to comprehensive, AI-driven care—a promising development we explore in depth.
[00:42:15] The Future of Agents in AI
We dive into the concept of “agents” in AI and how these systems may soon coordinate multiple models for more complex and precise clinical analyses.
[00:48:10] Where to Learn More about Dr. Nina Kottler’s Work
Nina shares where you can catch her upcoming talks and presentations, plus resources for staying updated on the latest in AI for radiology and digital pathology.

If you're a pathologist, radiologist, or healthcare professional curious about AI’s impact on diagnostics, this episode is packed with practical guidance on integrating AI into clinical workflows. Join us as we explore how AI is shaping the future of radiology and pathology!

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

113: DigiPath Digest #16 | PathVisions Recap, Ai in Breast Cancer Diagnostics and Global Health

8 november 2024 | 29 min

Welcome back to the DigiPath Digest, fresh from PathVision!

In this episode we will dive into the latest updates from the PathVision conference, covering trends in AI-driven diagnostics, the expansion of digital pathology into primary care, and the exciting new frontier of glassless pathology.

Join me as I recap the highlights of PathVision and the latest updates from the digital pathology literature, including discussions on:

AI Integration in Pathology: Learn how AI is advancing breast cancer diagnostics with tools like Ki-67 scoring models and multi-label AI for mammography, aimed at reducing unnecessary biopsies.

Global Health & Digital Microscopy: Hear about innovative projects from Sweden and Finland focused on AI-supported digital microscopy in primary healthcare labs, bringing accessible diagnostics to underserved areas.

Glassless Pathology with MUSE: Discover how glassless pathology is changing tissue imaging with MUSE (Microscopy with UV Surface Excitation), enabling diagnostics without the need for traditional glass slides. Dr. Zuraw breaks down what this means for future pathology workflows.

Plus, a shout-out to the vendors and partners making these advancements possible, and insights from Dr. Zuraw’s conversations with digital pathology trailblazers from around the globe, including new developments from Asia in digital pathology education and technology.

Timestamps:

[0:00] PathVision Highlights & Global Attendees
[5:15] AI in Diagnostic Workflows: Dr. Anil Parwani’s “Pathology Train Ride”
[12:30] Moving Beyond Narrow AI: Multimodal and Foundational Models
[18:45] Glassless Pathology: A New Frontier with MUSE Microscopy
[25:10] Integrating Digital Microscopy in Global Health Labs
[32:00] Breast Cancer Month: New Advances in AI for Diagnostics
[42:00] One Health & AI for Disease Detection in Primary Care
[48:30] Special Interviews: Jun Fukuoka and Asian Society of Digital Pathology

Links and Resources:

Publications Discussed Today:

📝 AI-Supported Digital Microscopy Diagnostics in Primary Health Care Laboratories: Protocol for a Scoping Review
🔗https://pubmed.ncbi.nlm.nih.gov/39486020/

📝 Ki-67 evaluation using deep-learning model-assisted digital image analysis in breast cancer
🔗https://pubmed.ncbi.nlm.nih.gov/39478421/

📝A Multi-label Artificial Intelligence Approach for Improving Breast Cancer Detection With Mammographic Image Analysis
🔗https://pubmed.ncbi.nlm.nih.gov/39477432/

📝 A comprehensive evaluation of an artificial intelligence based digital pathology to monitor large-scale deworming programs against soil-transmitted helminths: A study protocol
🔗 https://pubmed.ncbi.nlm.nih.gov/39466830/

If you enjoyed this episode, please subscribe and leave a review to

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

112: AI's GROWING ROLE IN THE FUTURE OF PATHOLOGY W/ Adam Cole and Jason Camilletti

2 november 2024 | 73 min

111: FDA and LDT's what does it actually mean for the labs? Kitchen chat w/ Dr. Thomas Nifong

19 oktober 2024 | 22 min

110: Can AI Improve Veterinary Diagnostics and Academic Efficiency w/ Candice Chu, DVM, PhD, DACVP, Texas A&M

17 oktober 2024 | 41 min

In this episode, I had a fascinating conversation with Candice Chu, DVM, PhD, DACVP, about how artificial intelligence (AI) is reshaping veterinary diagnostics and education. Candice, a clinical pathologist and educator at Texas A&M, is using AI tools like ChatGPT to improve efficiency in clinical workflows and academic processes. We explored the practical applications of AI, ethical concerns, and its future impact on veterinary medicine.

Key Topics Discussed:

[00:00:00] Introduction to AI in Veterinary Education and Diagnostics
I ask Candice how AI is changing veterinary education and diagnostics, and she explains how AI is boosting efficiency in both areas.
[00:01:00] Candice’s Journey in Veterinary Medicine
Candice shares her journey from Taiwan to the U.S., her career in veterinary pathology, and becoming an educator at Texas A&M.
[00:05:00] Custom GPT Model for Clinical Pathology
Candice describes the development of her custom GPT model for clinical pathology and its role in improving diagnostic efficiency.
[00:10:00] AI Tools for Academic and Clinical Efficiency
We talk about how AI tools reduce repetitive tasks, giving professionals more time for critical thinking and decision-making.
[00:14:30] Ethical Concerns When Using AI in Veterinary Medicine
Candice emphasizes the ethical responsibility of using AI, highlighting the importance of human judgment in AI-assisted diagnostics.
[00:20:00] How Veterinary Students Can Leverage AI
Candice shares tips on how students can use AI to enhance learning, from simplifying research to generating case questions.
[00:29:00] AI’s Role in Academic Writing and Veterinary Practice
We discuss how AI tools streamline academic writing and research, and how AI will continue shaping veterinary practice in the future.
[00:39:00] Critical Thinking and AI in Veterinary Medicine
Candice and I conclude by discussing how critical thinking and professional responsibility are essential when using AI tools.

Candice highlighted the transformative role AI can play in both veterinary education and diagnostics, improving efficiency while requiring responsible use. While AI tools like ChatGPT offer many benefits, the human element—our critical thinking and judgment—remains crucial in ensuring accurate results and ethical practices.

This episode provides practical insights on how veterinary professionals, educators, and students can harness AI to streamline workflows and improve diagnostic accuracy. Be sure to listen to the full conversation for actionable tips on integrating AI into your practice!

EPISODE RESOURCES:

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

109: How AI is Transforming Veterinary Diagnostics w/ Richard Fox, DVM, Dipl ECVP | Aiforia

15 oktober 2024 | 64 min

108: DigiPath Digest #14 (AI in Pathology: Case Prioritization, Kidney Biopsy Analysis and the Need for Consistent TIL Quantification).

11 oktober 2024 | 33 min

In this 14th episode of DigiPath Digest, I introduce a new course on AI in pathology, designed to help pathologists understand and confidently navigate AI technologies.

The episode focuses on various research studies that highlight the integration and effectiveness of AI in pathology, particularly in colorectal biopsies and kidney transplant biopsies, emphasizing the importance of seamless workflow integration.

You will also learn about challenges in manual assessment of tumor-infiltrating lymphocytes and HER2 expression in breast cancer. I advocate for more consistent and precise AI-driven approaches.

And there an opportunity for a discounted beta test of the new AI course.

00:00 Welcome to DigiPath Digest #14

00:24 New AI Course Announcement

01:51 Deep Learning in Colorectal Biopsies

09:17 AI in Kidney Biopsy Evaluation

16:12 Automated Scoring of Tumor Infiltrating Lymphocytes

24:22 AI for HER2 Expression in Breast Cancer

31:13 Conclusion and Course Details

THIS EPISODE'S RESOURCES

📰 A deep learning approach to case prioritisation of colorectal biopsies
🔗 https://pubmed.ncbi.nlm.nih.gov/39360579/

📰 Galileo-an Artificial Intelligence tool for evaluating pre-implantation kidney biopsies
🔗 https://pubmed.ncbi.nlm.nih.gov/39356416/

📰 Automated scoring methods for quantitative interpretation of Tumour infiltrating lymphocytes (TILs) in breast cancer: a systematic review
🔗 https://pubmed.ncbi.nlm.nih.gov/39350098/

📰 Precision HER2: a comprehensive AI system for accurate and consistent evaluation of HER2 expression in invasive breast Cancer
🔗 https://pubmed.ncbi.nlm.nih.gov/39350085/

▶️ YouTube Version of this Episode:
🔗 https://www.youtube.com/live/jkT8dTxelt4?si=xT6MNH7O4HuUnAN6

📕 Digital Pathology 101 E-book
🔗https://digitalpathology.club/digital-pathology-beginners-guide-notification

🤖 "Pathology's AI Makeover" Online Course 50% OFF
🔗 Let me know that you are interested in LinkedIn (just 10 spots available)

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

107: DigiPath Digest #13 (Revolutionizing Pathology with AI: Insights from PD-1 to Prostate Cancer Predictions)

9 oktober 2024 | 24 min

Good morning, digital pathology trailblazers! Welcome to another exciting exploration of digital pathology and AI. I’m thrilled to have our global community here with us today from so many different time zones. Before we dive into today's content, a quick note: my equipment is being a bit finicky, but that’s life in the digital world!

Integrating Image Analysis with AI

Let's kick off with a recap of some recent updates. Yesterday, I had the privilege of presenting to a mixed group at Cincinnati Children’s Hospital. We discussed AI in image analysis, an essential tool bridging radiology and pathology as these fields rapidly evolve with new technologies like foundation models and large language models. A diverse audience—ranging from radiologists to pathologists—prompted me to adapt my presentation style on the spot. It was a dynamic discussion about the advancements in healthcare that shared perspectives from both sides.

Lymphovascular Invasion: A Case Study

Our first paper today focuses on a deep learning model for identifying lymphovascular invasion (LVI) in lung adenocarcinoma. This significant prognostic factor is crucial for advancing diagnostic consistency and reliability. Unlike broad foundation models, this work engages with dedicated image analysis applications targeting specific diagnostic challenges. The study demonstrated reduced pathologist evaluation time by nearly 17% and even more in complex cases, aligning with previous findings that AI enhances efficiency by around 21%.

AI Collaborations: Human and Veterinary Pathology

Next, we delve into a collaborative effort between human and veterinary pathologists, emphasizing the promise of AI integration in telepathology and digital pathology. These fields are converging to enhance information exchange, teaching, and research. I’m particularly excited about this paper due to my own veterinary pathology background and the potential it offers for both educational and clinical practices.

Spatial Profiling and Immuno-Oncology

We then journey into the intricate landscape of immuno-oncology with a study on PD-1 and PD-L1 in osteosarcoma microenvironments. Utilizing deep learning and multiplex fluorescence immunohistochemistry, researchers highlighted the spatial orchestration of these markers, providing insights into potential immunotherapeutic strategies. This work is an exemplar of how AI can illuminate complex biological landscapes, offering a path for future therapies.

Conclusion

Thank you all for joining this vibrant discussion. Whether you’re tuning in from early morning in Atlanta or late at night in Algeria, your engagement enriches our learning experience. Keep an eye out for more content and upcoming courses designed to unpack these groundbreaking developments in AI and digital pathology.

Until next time, keep blazing trails in digital pathology!

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

106: Blind expert pathology opinions enabled digital pathology help win legal cases w/ Stephanie Franckewitz, JD, MBA

7 oktober 2024 | 56 min

105: Artificial intelligence in pathology Part 1 - the presentation I gave on the day I got engaged.

4 oktober 2024 | 27 min

104: DigPath Digest #12 (AI in Pathology: From Retinal Screening to Global Cancer Diagnostics + my new AI Co-Hosts)

27 september 2024 | 34 min

In this episode of DigiPath Digest you will learn about the development of AI models for glaucoma screening using fundus images, the use of AI in detecting metastatic deposits in colorectal cancer, and leveraging immunofluorescence data to reduce pathologist annotation requirements.

Dr. Aleks also invited two AI Co-hosts and shared personal reflections on AI's role in the industry and invites feedback from listeners on AI-generated content.

00:00 Introduction to the Livestream Disaster
00:24 AI to the Rescue: Enhancing Audio Quality
00:38 Meet the AI Co-Hosts
01:04 Welcome to the Digital Pathology Podcast
01:30 Technical Difficulties and Audience Interaction
02:49 Exploring AI in Veterinary Medicine
04:34 Hybrid Convolutional Neural Network for Glaucoma Screening
07:49 Model for Detecting Metastatic Deposits in Lymph Nodes
11:23 Leveraging Immunofluorescence Data for Lung Tumor Segmentation
18:05 AI-Generated Content and Future Plans
21:37 AI Co-Hosts Take Over
32:42 Conclusion and Audience Feedback

TODAY'S EPISODES RESOURCES
📰 Hybrid convolutional neural network optimized with an artificial algae algorithm for glaucoma screening using fundus images
🔗https://pubmed.ncbi.nlm.nih.gov/39301801/

📰 Automatic segmentation of esophageal cancer, metastatic lymph nodes and their adjacent structures in CTA images based on the UperNet Swin network
🔗https://pubmed.ncbi.nlm.nih.gov/39300922/

📰 Retrosynthetic analysis via deep learning to improve pilomatricoma diagnoses
🔗https://pubmed.ncbi.nlm.nih.gov/39298885/

📰 Obesity-Associated Breast Cancer: Analysis of Risk Factors and Current Clinical Evaluation
🔗 https://pubmed.ncbi.nlm.nih.gov/39287872/

📰 Model for detecting metastatic deposits in lymph nodes of colorectal carcinoma on digital/ non-WSI images
🔗 https://pubmed.ncbi.nlm.nih.gov/39285483/

📰 Leveraging immuno-fluorescence data to reduce pathologist annotation requirements in lung tumor segmentation using deep learning
🔗 https://pubmed.ncbi.nlm.nih.gov/39284813/

📰 Bayesian Landmark-based Shape Analysis of Tumor Pathology Images
🔗 https://pubmed.ncbi.nlm.nih.gov/39280355/

📰 Globalization of a telepathology network with artificial intelligence applications in Colombia: The GLORIA program study protocol
🔗 https://pubmed.ncbi.nlm.nih.gov/39280257/

📰 Towards next-generation diagnostic pathology: AI-empowered label-free multiphoton microscopy
🔗 https://pubmed.ncbi.nlm.nih.gov/39277586/

📰 Sex differences in sociodemographic, clinical, and laboratory variables in childhood asthma: A birth cohort study
🔗 https://pubmed.ncbi.nlm.nih.gov/39019434/

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

103: DigiPath Digest #11 (Pathology & AI: Metastasis Detection, Fast Annotations & Foundation Models)

23 september 2024 | 35 min

In this episode of DigiPath Digest, we review the latest AI developments in digital pathology described in the literature. I explore how AI is pushing the boundaries of metastasis detection, breast cancer treatment predictions, lung cancer research trends, and the creation of pathology foundation models.

Episode Breakdown:

00:00 – Welcome & Introduction
00:36 – Sentinel Node Metastasis Detection: A discussion on the development of an AI model that can detect sentinel node metastasis in melanoma with accuracy comparable to that of pathologists. The model aids in distinguishing between nodal metastasis and intra-nodal nevus, which is crucial for accurate staging in melanoma patients.
05:01 – Predicting Breast Cancer Treatment Response: A cross-modal AI model that integrates pathology images and ultrasound data is explored. This model is designed to predict a breast cancer patient’s response to neoadjuvant chemotherapy, providing personalized insights that can guide treatment decisions.
09:59 – Global Trends in AI and Lung Cancer Pathology: This section reviews a bibliometric study that analyzed global research trends in AI-based digital pathology for lung cancer over the past two decades. The study highlights the need for increased collaboration between institutions and countries to further AI advancements in this area.
13:30 – Pathology Foundation Models: An in-depth look at a new foundation model in pathology, designed to generalize across various diagnostic tasks. This model shows significant promise in cancer diagnosis and prognosis prediction, outperforming traditional deep learning methods by addressing domain shifts across different datasets.
20:08 – Domain Shifts in AI Models: A brief discussion on the impact of domain shifts, such as variations in staining protocols and patient populations, on the performance of AI models in pathology. Strategies for mitigating these challenges are highlighted.
29:09 – Faster Annotation in Pathology: The episode concludes with a review of a study comparing manual and semi-automated annotation methods. The semi-automated approach significantly reduces the time required for annotating whole slide images, offering a more efficient solution for pathologists.

Resources Mentioned:

📰 Sentinel Node Metastasis Detection in Melanoma
🔗 https://pubmed.ncbi.nlm.nih.gov/39238597/

📰 Cross-Modal Deep Learning for Breast Cancer Response
🔗 https://pubmed.ncbi.nlm.nih.gov/39237596/

📰 Global Bibliometric Mapping in Lung Cancer Pathology
🔗 https://pubmed.ncbi.nlm.nih.gov/39233894/

📰 CHIEF Foundation Model for Cancer Diagnosis
🔗 https://pubmed.ncbi.nlm.nih.gov/39232164/

📰 Improving Annotation Processes in Pathology
🔗 https://pubmed.ncbi.nlm.nih.gov/39231887/

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

102: DigiPath Digest #10 (From HER2 Low to Gleason Grading: AI in Digital Pathology Research)

30 augusti 2024 | 29 min

101: Image Analysis Enhances Pathology Evaluation of Preclinical Studies, not Replaces it

28 augusti 2024 | 35 min

📄 Learn more about GLP-compliant tissue image analysis at Charles River Laboratories.

Today my guest is Danielle Brown, a fellow veterinary pathologist, the General Manager at Charles River Laboratories Reno, Nevada, and a pioneer in the use of image analysis for toxicologic pathology. Together, we explored the ever-evolving role of image analysis in preclinical studies and how it enhances, rather than replaces, the expertise of pathologists.

This conversation is a deep dive into the intersection of pathology and technology, showcasing how image analysis is revolutionizing preclinical research. We also discuss the future of this technology and its implications for the industry.

Join us as we navigate the intricacies of image analysis, share insights on the collaborative process between pathologists and image analysis scientists, and look ahead to the exciting advancements on the horizon.

Key Discussion Points:

[00:00:00] Introduction and Guest Welcome:
- Introducing Danielle Brown and her significant contributions to the field of toxicologic pathology.
[00:02:46] The Role of Image Analysis in Preclinical Drug Development:
- Why image analysis is crucial for accurate and efficient evaluations in preclinical studies.
[00:03:23] Challenges and Limitations of Visual Analysis:
- Discussing the limitations of visual analysis and how image analysis overcomes these challenges.
[00:08:06] Pathologist and Image Analysis Collaboration:
- The importance of collaboration between pathologists and image analysis scientists to ensure accurate data interpretation.
[00:13:00] Efficiency and Cost of Image Analysis vs. Pathologist Scoring:
- Comparing the efficiency, cost, and consistency between image analysis and traditional pathologist scoring methods.
[00:15:18] Validation and Qualification of Image Analysis Algorithms:
- The process of validating image analysis algorithms to ensure they meet regulatory standards in a GLP environment.
[00:19:54] GLP Compliance and Regulatory Considerations:
- How Charles River ensures GLP compliance in their image analysis processes, making them suitable for regulatory submissions.
[00:23:27] Method Development for Specific Stains and Techniques:
- Approaching projects that require new method development or specialized procedures.
[00:27:46] Future of Image Analysis in Pathology:
- Danielle’s insights into the future of image analysis and how emerging technologies will shape the field.

This episode is packed with valuable insights and practical advice for anyone involved in preclinical research or interested in the integration of image analysis in pathology. Danielle’s expertise and our discussion provide a roadmap for leveraging image analysis to increase evaluation efficiency and the granularity of your data.

THIS EPISODE'S RESOURCES:

📄 The paper Aleks and Danielle co-authored: "Developing a Qualification and Verification Strategy for Digital Tissue Image Analysis in Toxicological Pathology"

▶️ Watch the full episode here: Image Analysis Enhances Pathology Evaluation of Preclinical Studies, not Replaces it.

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

100: AI in Pathology: DigiPath Digest #9 (From Retinal Assessment to Tumor Prognostics)

23 augusti 2024 | 43 min

In this episode, we celebrate the 100th edition of the Digital Pathology Podcast!
Thank you so much for being part of this journey!
You are my Digital Pathology Trailblazers and I prepared a Digital Pathology Trailblazer manifesto for us!

This is the 9th edition of DigiPath Digest, and we are attracting more and more people to this series.

I am also working on a new YouTube digital pathology course and am offering the first 100 enrollments for free in exchange for feedback.

During today's episode, we cover several papers including research on AI for predicting post-operative liver metastasis, validation of AI-based breast cancer risk stratification models, AI applications in clinical microbiology, advances in parasitology diagnostics, AI for retinal assessment, and AI models for detecting microsatellite instability in colorectal cancer.

We also unveil a Digital Pathology Trailblazer manifesto emphasizing the ethos and dedication of the community.

Join us to stay current with literature, advancements, and insights from the fascinating world of digital pathology.

00:00 Introduction and Announcements
00:25 Live Podcast Proposal
01:40 Welcome and Audience Interaction
03:05 Updates and Apologies
06:11 YouTube Course Announcement
07:23 Technical Difficulties and Solutions
10:00 Digital Pathology Club and Vendor Sessions
11:28 First Research Paper Discussion
17:38 Second Research Paper Discussion
20:07 ER Positive and HER2 Negative Patient Subgroup Analysis
20:59 Independent Prognostic Value of StratiPath Breast Solution
21:59 Challenges and Benefits of Image-Based Stratification
22:58 Technical Difficulties and Live Stream Interaction
24:22 Introduction to Paper Number Three: AI in Clinical Microbiology
28:07 AI in Parasitology Screening and Diagnosis
29:30 Physics-Informed AI for Retinal Assessment
33:08 AI for Microsatellite Instability Detection in Colorectal Cancer
36:42 YouTube Course Announcement and Digital Pathology Trailblazer Manifesto
42:25 Celebrating the 100th Episode of the Digital Pathology Podcast

THE ABSTRACTS WE COVERED TODAY

📄 A novel model for predicting postoperative liver metastasis in R0 resected pancreatic neuroendocrine tumors: integrating computational pathology and deep learning-radiomics.
https://pubmed.ncbi.nlm.nih.gov/39143624/

📄 Validation of an AI-based solution for breast cancer risk stratification using routine digital histopathology images
https://pubmed.ncbi.nlm.nih.gov/39143539/

📄 Potential roles for artificial intelligence in clinical microbiology from improved diagnostic accuracy to solving the staffing crisis
https://pubmed.ncbi.nlm.nih.gov/39136261/

📄No longer stuck in the past: new advances in artificial intelligence and molecular assays for parasitology screening and diagnosis
https://pubmed.ncbi.nlm.nih.gov/39133581/

📄Physics-informed deep generative learning for quantitative assessment of the retina
https://pubmed.ncbi.nlm.nih.gov/39127778/

📄Artificial Intelligence Models for the Detection of Microsatellite Instability from Whole-Slide Imaging of Colorectal Cancer
https://pubmed.ncbi.nlm.nih.gov/39125481/

▶️ YouTube Version of this Episode
https://www.youtube.com/live/Uwca5rzAtEA?si=Rd8r4LVM1utEKWdt

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

99: DigiPath Digest #7 (Exploring AI-driven advances in digital pathology from T-cell signatures to synthetic images)

9 augusti 2024 | 44 min

98: DigiPath Digest #6 (Foundation models high level overview)

2 augusti 2024 | 50 min

97: DigiPath Digest #5 (AI in Modern Medicine: Diagnostics and Healthcare Outcomes)

26 juli 2024 | 46 min

96: Achieving Work-Life Balance in Medicine as a Pathologist with Digital Pathology w/ Todd Randolph, MD

24 juli 2024 | 58 min

95: DigiPath Digest #3 (AI and Digital Pathology: Innovations in Disease Detection and Prognosis Abstract Review)

12 juli 2024 | 35 min

94: Dr. Aleks Zuraw on "People of Pathology" Podcast | Digital Pathology 101 Book

10 juli 2024 | 48 min

Watch the full episode here

This episode was originally recorded for "People of Pathology Podcast" and I had the pleasure of being interviewed by Dennis Strenk after I have published my book "Digital Pathology 101 - All you need to know to start and continue your digital pathology journey". This was my third appearance on his show, so I was really honored!

Our talk about digital pathology focused on the cultural shift and learning mentality essential for embracing rapid advancements in the field.

We highlighted the importance of open-mindedness, interdisciplinary collaboration, and the practical applications of AI to enhance diagnostic and workflow processes.

I also shared insights from my book, "Digital Pathology 101," which Dennis called "a comprehensive resource for beginners and experts". We covered key topics such as regulatory milestones, interoperability, and the role of toxicologic pathology.

CHAPTERS

earning Mentality (00:00): Exploring the mindset required for adapting to new technologies in digital pathology.
Welcome to the Digital Pathology Podcast (00:53)
The Journey of Writing Digital Pathology 101 (02:03): Sharing the process and inspiration behind writing the book.
Balancing Content for Different Readers (05:29): How to make the book accessible and valuable for newcomers and seasoned professionals.
Digital Pathology Milestones and Surprises (10:27): Highlighting significant achievements and unexpected developments in the field.
Interoperability in Digital Pathology (15:19): The importance of systems working together seamlessly.
Collaborating with Vendors (17:29): The benefits and challenges of working with technology providers.
The Cultural Shift in Digital Pathology (21:47): Emphasizing the need for a cultural change within the pathology community to embrace digital tools fully.
AI in Pathology: Narrow vs. General AI (27:17): Differentiating between specific AI applications and broader AI capabilities.
Companion Diagnostics and Personalized Medicine (35:34): The role of digital pathology in advancing personalized medicine.
The Role of Toxicologic Pathology (38:49): Discussing the role of toxicologic pathology in the digital age.
Conclusion and Final Thoughts (42:37): Wrapping up the discussion with reflections and future outlooks.

It was great to be Dennis' guest instead of the host this time, and be able to talk about digital pathology and the book to his audience. I liked this episode a lot and I hope you will to.

To learn digital pathology fast, be sure to check out my book "Digital Pathology 101." You can get your copy here: Digital Pathology 101 E-book.

THIS EPISODE'S RESOURCES

The original audio version of Dennis' podcast is here:
🎧

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

93: DigiPath Digest #2 (Why Digital Pathology Newsletter Audio Died and What I Am Doing Instead)

7 juli 2024 | 45 min

92: Radiology's Digital Transformation: Lessons for Pathology's Journey w/ Greg Rose, MD, PHD

30 maj 2024 | 78 min

91: Using AI in Pathology to Benefit Patients w/ Mariano de Socarraz, CorePlus

26 april 2024 | 64 min

In this episode Dr. Aleks Zuraw sits down with Mariano De Socarraz, President of CorePlus and member of the board of directors at the Digital Pathology Association.

CorePlus is an anatomic and clinical pathology lab in Puerto Rico that has fully embraced digital pathology and AI.

Key Takeaways

CorePlus converted to 100% whole slide imaging for primary diagnosis in January 2020, before the pandemic
They are pioneering the use of AI algorithms from companies like IBEX, AlpenGlow, Artera and TechCyte for cancer detection and precision pathology
Digital pathology increases efficiency by ~30% and enables benefits like remote reading, better ergonomics, and seamless sharing of cases
AI helps detect missed lesions, reduce interoperator variability, and eliminate false negatives in prostate biopsies
The future of pathology will involve predictive and prognostic information generated right from digital slides (histomics)

Making the Digital Transition

Mariano shares how CorePlus, as a technology-forward company, decided in 2018 to fully convert to digital pathology. They took 2019 to prepare, validate their processes following CAP guidelines, and get full buy-in from stakeholders. On January 1st, 2020 they were fully digital.

While acknowledging that glass slides have advantages in simplicity, Mariano believes the benefits of digital pathology for patients and pathologists are too great to ignore. His advice for other practices considering the digital transition:

Focus on re-engineering your workflows first before choosing scanners
Plan for IT redundancy to avoid any disruption
Get full buy-in from your team
Start focused and build successes in stages

Unlocking the Power of AI

After seeing a press release about UPMC and IBEX using AI to diagnose prostate cancer, CorePlus reached out to partner with them. They became the first site outside the UK to validate and implement IBEX's algorithm, running it on over 9500 cases as a QC tool.

The algorithm was able to alert pathologists to missed lesions in 73 patients that would have otherwise been false negatives. CorePlus has now moved the algorithm to the front-end to pre-screen and triage all prostate cases.

They are also partnering with other AI companies like AlpenGlow, Artera and TechCyte to bring these benefits to breast, GI, cytology and other subspecialties. Mariano sees AI generating predictive and prognostic insights right from slides.

The Future is Digital

Mariano believes medical education must quickly incorporate digital pathology and AI training to prepare the next generation of pathologists. The Digital Pathology Association is key in fostering collaboration to expand access, especially in underserved communities.

While going digital requires some reinvention, Mariano is excited to pioneer this space. He and CorePlus aim to be "missionaries" doing what's best for patients and the field of pathology.

THIS EPISODE'S RESOURCES:

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

90: Swarm Learning: The Future of AI Collaboration in Digital Pathology w/ Oliver Saldanha

19 april 2024 | 54 min

Swarm Learning in Digital Pathology: Revolutionizing Cancer Histopathology

Today on the Digital Pathology Podcast my guest is Oliver Saldana, the first author of a significant Nature Medicine paper published in 2022 on 'Swarm Learning for Decentralized Artificial Intelligence in Cancer Histopathology'.

Oliver shares his journey from Mangalore, India, to Germany, where he pursued his master's and PhD, delving into histopathology and decentralized AI under the supervision of Professor Dr. Jakob Nicolas Kather.

The discussion explores the concept of swarm learning as a novel method for deep learning in histopathology, its advantages over centralized learning including compliance with data protection laws like GDPR, and its potential for global collaboration in medical research without sharing sensitive data.

Oliver emphasizes swarm learning’s ease of setup and its alignment with the FAIR principles for scientific data management. The podcast aims to shed light on the groundbreaking work being done in the convergence of pathology and computer science, urging researchers and pathology centers to digitize their slides and contribute to global swarm learning projects.

00:00 Introduction to Swarm Learning and Its Applications
00:50 Intro
01:17 Meet Oliver Saldana: A Trailblazer in Decentralized AI for Cancer Histopathology
03:57 Exploring the Concept of Decentralized AI and Its Importance
06:52 Understanding Centralized vs. Decentralized Learning
08:47 The Revolutionary Approach of Swarm Learning
10:38 Blockchain's Role in Enhancing Histopathology with Swarm Learning
14:50 Addressing Preprocessing and Generalizability in Swarm Learning
21:26 Swarm Learning's Compliance with GDPR and Data Protection
25:05 Exploring Swarm Learning in Medical Data Analysis
25:34 Prototype Study and Real Cohorts in Swarm Learning
27:01 Comparing Swarm Learning with Centralized Models
27:44 The Role of Bare Metal Servers in Swarm Learning
30:01 Centralized Slide Repositories vs. Swarm Learning
44:11 Commercializing Swarm Learning Models
47:07 FAIR Principles and Swarm Learning
51:11 Global Ambitions and the Future of Swarm Learning

THIS EPISODES RESOURCES

📝 Swarm Learning for decentralized and confidential clinical machine learning
🔗 https://www.nature.com/articles/s41586-021-03583-3

📝The FAIR Guiding Principles for scientific data management and stewardship
🔗https://www.nature.com/articles/sdata201618

🎧BIGPICTURE – THE LARGEST WHOLE SLIDE REPOSITORY FOR AI MODEL DEVELOPMENT IN PATHOLOGY. WHERE DO WE STAND AT MONTH 15/72?
🔗https://digitalpathologyplace.com/podcast/bigpicture-the-largest-whole-slide-repository-for-ai-model-development-in-pathology-where-do-we-stand-at-month-15-72/

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

89: Navigating Ethical Challenges in AI-Powered Pathology | Webinar recording

18 april 2024 | 55 min

Navigating Ethical Challenges in AI-Powered Pathology

This episode is a webinar recording.
It delves into the complex ethical considerations of incorporating artificial intelligence (AI) in pathology.

Dr. Zuraw begins by exploring the fundamentals of ethics and moves on to discuss the impact of AI in pathology, focusing on:

ethical dilemmas,
data diversity issues,
biases, and
the importance of maintaining professional and societal ethical standards in the wake of AI integration.

The session touches upon the ethical guidelines and regulatory frameworks guiding ethical decision-making in healthcare, alongside the role of regulatory agencies like the FDA.

It also highlights the significance of data diversity and mitigation strategies to address potential ethical pitfalls in AI utilization.

The webinar emphasizes the constant balance between advancing technology and ethical responsibility, underlining the need for transparency, governance, and accountability in deploying AI tools in pathology.

00:00 Introduction to Ethics in AI-Powered Pathology
00:30 Exploring the Ethical Dilemmas in Healthcare
00:36 Webinar Overview and Digital Pathology Insights
01:05 Defining Ethics and Its Importance in AI Pathology
02:05 Interactive Webinar Engagement and Audience Participation
03:25 Deep Dive into Ethics: Definitions and Applications
09:31 Ethical Considerations in Biomedical Research
10:34 Navigating Ethical Dilemmas: A Practical Example
13:57 Understanding Ethical Principles in Decision Making
17:14 AI Bias and Representation in Pathology
20:52 Frameworks and Guidelines for Ethical Oversight
25:02 AI Applications in Pathology: Ethical Perspectives
27:21 Exploring AI in Research and Its Capabilities
29:22 AI's Role in Medical Imaging and Diagnostics
33:11 Ethical Considerations and AI in Pathology
34:04 Addressing AI Challenges: Bias, Interpretability, and Security
44:26 AI as a Medical Device: Regulatory Perspectives and Future Directions
49:16 Concluding Thoughts and Audience Engagement

THIS EPISODES RESOURCES:

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

88: Artificial Intelligence & Machine Learning: Transforming Pathology | Webinar

11 april 2024 | 65 min

If any of the statements applies:

➡️ You know AI and Machine Learning are already part of the pathology workflow, but maybe you are not exactly sure which part of the workflow?

➡️ “AI” is still a bit of overhyped, fuzzy buzzword for you?

➡️ You would like to learn about how it can help pathologist and labs work smarter and patients get better care.

Then this webinar is for you!

This is the second part of the “Digital Pathology 101” webinar series, based on the “Digital Pathology 101” book, where Dr. Aleks Zuraw explains digital pathology and AI concepts.

This journey through Chapter 3 illuminates how image analysis, AI, and machine learning not only complement traditional pathology but propel it into new realms of precision and insight.

As we delve into the essence of tissue image analysis and the transformative role of AI and machine learning in modern pathology, you'll discover how these technologies augment diagnostic methods, enhance research, and redefine what's possible in our field.

From the basics of tissue image analysis to the advanced realms of computer vision and the pivotal role of quality control, this webinar bridges the gap between high-level computational domains and daily pathology practice.

What You'll Explore:

The foundational principles of image analysis, AI, and machine learning in pathology.
The crucial balance between classical and AI-based approaches to tissue image analysis and their applications in both regulated and non-regulated environments.
The importance of quality control in ensuring accurate, reliable results from AI-assisted analyses.
An introduction to the key terminology of pathology informatics, demystifying the language that underpins digital pathology and AI.
Who Should Attend:
This webinar is tailored for:

🔴 pathologists,

🔴 researchers, and

🔴 healthcare professionals

who are eager to learn about and/or integrate AI and machine learning into their work.

Whether you're just starting or looking to deepen your expertise in digital pathology, this series offers invaluable insights into leveraging technology for enhanced diagnostic precision and patient care.

Date and Time:
April 11, 2024 at 9:00 - 10:30 a.m., EST

Location:
Online

AI is here, so let’s learn what it means for pathology

how can you leverage it for your work?

and how to navigate this new technology responsibly.

Looking forward to seeing you on the inside!

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

87: Digital Pathology Applications. From Clinical Practice to Drug Development | Webinar

7 april 2024 | 54 min

86: Current Digital Pathology Trends: Post-conference Recap from USCAP 2024 (Unscripted)

31 mars 2024 | 52 min

This week, the digital pathology community gathered at the United States and Canadian Academy of Pathology (USCAP) annual meeting in Baltimore. I had the incredible opportunity to attend, spurred by an invitation from Hamamatsu, known for their revolutionary digital pathology scanners like the FDA-cleared S360 and the new S20 model.

Key Takeaways from USCAP:

Innovative Partnerships and Technology: My agenda was filled with meetings that explored the latest in digital pathology. Key highlights include the launch of Hamamatsu's S20 scanner, Techcyte's technological advancements, and Proscia's FDA-approved AP Dx software. The collaboration between Hamamatsu and Agilent, utilizing Proscia's platform, underscored the collaborative spirit driving the field forward.
Community Engagement and Recognition: The warmth and recognition from the community were overwhelming. It reinforced the value of our work and the podcast, blending technical insights with personal stories that underline the human aspect of pathology.
Advancing Research and Education: A standout moment was learning about the World Tumor Registry initiative from Andrey Bychkov and Alyaksandr Nikitski. This initiative marks a significant step in making valuable pathological data more accessible for research and education, starting with a comprehensive collection of thyroid case slides.

Looking Forward:
The USCAP meeting was a testament to the enthusiasm and innovation within digital pathology. Stay tuned for a detailed video blog covering the conference, highlighting the S20 and more, coming soon on YouTube!

USCAP BULLET UPDATES

Hamamatsu: Known for their FDA-cleared scanner, S360, and the newly launched S20 model.
Techcyte: Discussed their dynamic evolution and upcoming projects and their partnership with BD for cervical cytology AI based evaluation.
Corista: Learned about their software advancements, including voice recognition for improving pathologist workflows.
Smart In Media: Discussed their new camera for microscopes and grossing rooms.
Proscia: Celebrated their FDA clearance for the AP Dx software.
Epredia: Showcased their pathology equipment, including scanners like the P1000 with water immersion.
Aiforia: Highlighted their AI for image analysis, especially the GLP-compliant module for toxicologic pathology.
Indica Labs: Featured their pathologist cockpit setup and discussed their comprehensive software solutions.
PathPresenter: Met with the CEO, Patrick Myles, and discussed the company's rapid growth and services.
Pramana: Discussed their archival scanning services and their new benchtop scanner that runs algorithms during scanning.
Grundium: Showed off their new four-slide scanning Ocus and the cute one-slide Ocus scanner.
Andrej Bychkov to discuss his poster on the use of ChatGPT by pathologists and told me abou

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

85: Digital Pathology for Community Hospitals | Dr. Elizabeth Plocharczyk

26 mars 2024 | 55 min

She did it all on her own, to keep serving her patients.

In this episode of Digital Pathology Podcast, host Dr. Aleksandra Zuraw is joined by Dr. Elizabeth Plocharczyk, a pathologist based in Ithaca, New York.

Beth shares her experience integrating digital pathology into her practice at Guthrie Cortland Medical Center and Cayuga Medical Center at Ithaca, NY. Her journey offers insights into the practicalities of adopting digital tools in a community hospital setting.

🔥 The discussion highlights:

The factors that influenced Beth to start using digital pathology.
How digital tools have addressed challenges related to being a solo practitioner in a rural area.
The significance of compliance, internal validation, and administrative support in transitioning to digital pathology.
Suggestions for pathologists considering digital pathology, emphasizing iterative implementation and the importance of validation regardless of FDA approval status.

Dr. Plocharczyk's account underscores the role of digital pathology in enhancing the efficiency and flexibility of pathology practice, especially in geographically constrained settings.

The episode provides a REALISTIC OVERVIEW OF TRANSITIONING TO DIGITAL PATHOLOGY, including overcoming potential hurdles and leveraging technology for more effective pathology services.

Be sure to watch or listen to the full episode, as Dr. Plocharchyk reveals all the details about the equipment she used, the way she validated the system as well as her budget.

This episode is particularly relevant for pathologists and healthcare professionals exploring digital pathology's potential to improve practice management and patient care.

Questions that will be answered:

Who is Dr. Beth? What did her pathology practice look like before digital pathology?
When did Dr. Beth start using digital pathology?
What was impossible before going digital?
How did you determine which tools to use?
Why did you opt for Whole Slide Imaging, for frozen sections?
What was the budget and how did you know this is a reasonable budget?
How long have you had the equipment?
If budget was not a constraint, what would you add to your digital pathology arsenal?
Are you building your tools or seeking the help of a third-party provider?
What does the day-to-day practice with your digital pathology tools look like?
How have the community hospitals responded to the new cutting-edge technology?
What advice would you give to those starting with digital pathology?
Would digital pathology help you grow your practice?

THIS EPISODE RESOURCES:

Smart in Media PathoZoom Live View and Scan:
🔗 https://www.youtube.com/watch?v=PZA9HX3qSfk&list=UULF-bagVf7bqp3L0bAdNYaaQg

Grundium Ocus Whole Slide Scanner:
🔗 https://www.youtube.com/watch?v=dq-vdOL9Q9Q&list=UULF-bagVf7bqp3L0bAdNYaaQg

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

84: Remote Second Opinion. The Perfect Digital Pathology Use Case w/ Dr. Rajendra Singh, PathPresenter

11 mars 2024 | 46 min

Remote Digital Second Opinions: Pioneering Global Patient Care

Imagine a future where accessing world-class diagnostic expertise is just a click away for any patient, anywhere. In this episode you will learn how remote digital second opinions, a specialized application of digital pathology, can drive global adoption of digital pathology and significantly expand access to patient care.

Together with Dr. Raj Singh, founder of PathPresenter, we explore this cutting-edge approach that promises to transcend current digital pathology uses, making specialized medical consultations more accessible and efficient than ever before.

The Evolution of Digital Pathology

Digital pathology is rapidly becoming indispensable in modern healthcare. It equips pathologists with advanced digital tools and platforms, significantly boosting the speed and scope of diagnoses. Remote second opinion has a transformative role here. By leveraging digital slides and cloud-based infrastructure, pathologists can collaborate seamlessly across distances, breaking down geographical barriers like never before.

PathPresenter: Filling the Gaps in Pathology Workflow

Dr. Singh unfolds the story behind PathPresenter, highlighting its inception, mission, and the significant void it fills within the pathology field. PathPresenter is more than a platform; it's a catalyst for bridging educational and clinical gaps in pathology. It enables effortless sharing and collaborative analysis of cases among pathologists globally, fostering a vast network of professional expertise.

Embracing the Digital Shift: A Call to Action

The shift towards digital workflows is not merely a technological leap but a comprehensive strategy to enhance patient care, ensuring diagnoses are faster, more accurate, and widely accessible.

The transition to digital pathology is inevitable and it is happening quickly. Dr. Singh emphasizes the urgency for pathologists and healthcare institutions to adapt to these technological advances proactively. Proactive adoption will give us the power to decide how we want to implement digital pathology and what tools we want to use. If the pathology community does not take charge of this process it will be imposed on us by others. We don't want to figure out how to digitize slides in a panic mode when other specialties require it for patient care. We want to be in the drivers seat and guide the patient care according to the most up-to-date pathology expertise.

Why This Matters More Than Ever

In an era where healthcare demands are ever-increasing, and the need for specialized knowledge is paramount, digital pathology and remote second opinions present an unprecedented opportunity. This application democratizes access to expert diagnostics, ensuring patients, regardless of location, receive the best care possible.

It's more than an advancement; it's a new way of thinking about and delivering pathology services. Explore the vast possibilities remote second opinions offer and how they serve as a bridge to a more connected, efficient, and patient-centric healthcare system.

THIS EPISODE'S RESOURCES

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

83: The Evolution of Pathology on the Web and Beyond w/ Keith Kaplan, MD | tissuepathology.com

5 mars 2024 | 57 min

Today our special guest is Dr. Keith Kaplan, the creator of TissuePathology.com himself! The publisher of a platform that inspired the creation of Digital Pathology Place.

The Digital Pathology Trailblazer on the Web

Dr. Keith Kaplan, a surgical pathologist and a pivotal figure in the digital pathology community, has significantly contributed to the field with his groundbreaking website, tissuepathology.com. His passion and dedication have made his platform the first resource many turn to when searching for anything related to digital pathology.

From Traditional to Digital

Dr. Kaplan's unique journey in pathology began in Chicago, shaped by his military service and academic path at Northwestern University. His early exposure to telepathology and digital imaging during his military tenure set the stage for his impactful venture into digital pathology, initiating a transformative career trajectory.

TissuePathology.com: A Pioneering Platform

Dr. Kaplan launched tissuepathology.com, driven by his enthusiasm for utilizing the internet to disseminate knowledge. This platform quickly became a leading blog in the digital pathology realm, motivating others to establish their blogs and engage in the dynamic digital pathology conversation.

The Evolution of Digital Pathology

Keith's work with robotic telepathology and his involvement in deploying digital pathology solutions across various settings highlight the significant advancements in the field. His stories of early digital pathology efforts, including the deployment of systems for military applications and the subsequent adoption in civilian medical practice, showcase the progressive integration of technology in pathology.

Embracing Change: The Digital Shift

Recently Dr. Kaplan's practice transitioned to digital pathology for primary diagnosis. The integration of digital pathology has streamlined diagnostic processes, enabling faster and more efficient patient care despite initial reservations about moving away from traditional microscopy.

Future Directions and Ongoing Challenges

Looking ahead, the future of digital pathology will be impacted by AI and the ongoing pathology workforce shortage. Keith emphasizes the need for the pathology community to adapt and embrace new technologies while also addressing regulatory, ethical, and practical challenges.

THIS EPISODE's RESOURCES:

THIS EPISODE's RESOURCES:

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

82: Digital Pathology Newsletter no. 2 (26 Jan 2024)

26 januari 2024 | 16 min

81: No More Microscopes. How close are we to glassless pathology? | w/ Dr. Richard Levenson, UC Davis Health

17 januari 2024 | 73 min

Can pathology be truly digital without getting rid of glass?

In this episode with Dr. Richard Levenson, Professor and Vice Chair for Strategic Technologies at the Pathology Department of UC Davis, you’ll learn how close we are to “glassless pathology” and other digital innovations that could transform the field.

In this episode we cover:

Richard's Background

With an eclectic background spanning English literature, medical school, research, and even a tech startup, Richard brings unique expertise in digital pathology. At UC Davis, he's pioneering new microscopy methods like MUSE and FIBI that enable imaging thick tissue sections without slides or stains.

Pigeon Research

You may also know Richard for his famously viral research training pigeons to detect cancer in pathology slides. As he explains, “Pigeons have the skills to tell...tiny, tiny pattern differences” critical for pathological diagnosis. This project brought fun and creativity to his lab, even as they push new frontiers in glassless pathology.

Histolix and Glassless Pathology

His company Histolix is commercializing the glassless pathology approach, which Richard envisions bringing pathology on par with radiology’s direct-to-digital workflow. Their validation study already achieved 97% concordance between glassless and standard H&E reads. As Richard explains, these techniques “open up the possibility for rapid intraoperative diagnosis without freezing or sectioning.”

Digital Pathology Innovation

Combined with AI, innovations like these could automate workflow steps like staining, analysis, and prioritization. However, as their recent paper explores, AI does pose risks. Richard believes we must tread carefully, using human oversight and judgment to guide implementation. Still, he sees great potential to augment diagnostics with computational tools.

Conclusion

There’s no better guide to exploring these frontiers than Richard. Tune into the full conversation using the link above for an insightful tour of digital pathology’s cutting edge. Check Histolix for the latest on their research, and access key publications from Richard’s lab through the links below. Where will you help take pathology next?

THIS EPISODES RESOURCES

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

80: Digital Pathology Newsletter no. 1 (10 Jan 2024)

10 januari 2024 | 11 min

79: How AI is Transforming Pathology in Developing Countries | Digital Pathology in Pakistan w/ Talat Zehra

22 december 2023 | 34 min

78: Exploring Open-Source for Tissue Image Analysis and Data Science Business w/ Trevor McKee, Pathomics.io

7 november 2023 | 31 min

Exploring Image Analysis Innovation with Trevor McKee of Pathomics.io

If you work in digital pathology, you likely rely on image analysis tools to gain insights from complex visual data. But how do you stay on top of the latest innovations in this fast-evolving field?

In this podcast episode together with Trevor McKee, CEO of Pathomics.io, we discuss innovation in image analysis using open source tools.

Pathomics takes an innovative approach by building image analysis solutions on open source platforms like QuPath. As Trevor explained, open source fosters collaboration, democratizes access, and drives rapid advances - key in a fast-moving field like digital pathology. This enables rapid progress that proprietary systems can't match.

Trevor's Career Journey

Trevor’s journey lead him from chemical engineering into pioneering image analysis, inspired by solving complex biological problems. His diverse experiences, from photon imaging at MIT to leading a core lab facility, fueled a passion for leveraging image analysis to extract insights. Today, in addition to leading Pathomics.io he is an Adjunct Lecturer at the University of Toronto, and the Chief Scientific Officer at BioCache™ Lab Solutions.

Transparent and Reproducible Image Analysis & Explainable AI

A core ethos at Pathomics is making image analysis transparent and reproducible. through explainable AI techniques. Tools like XGBoost create models that are easier to interpret than "black-box" end-to-end neural networks. This builds trust and acceptance among the scientific community.

Streamlining Workflows

In addition, Pathomics develops solutions to streamline clients' image analysis workflows. For example, their Universal StarDist plugin makes it easy to run advanced models like StarDist in QuPath. Overall, the goal is to automate tedious tasks so you can concentrate on high-value decision making.

The Future of Image Analysis

Looking ahead, Trevor shared his vision for an AI-powered online platform enabling users to go seamlessly from images to insights. He also discussed open wikis to prevent redundant work and encourage knowledge sharing as the field rapidly evolves.

Trevor plans to launch it to catalogue digital pathology resources such as image analysis focused machine learning papers to prevent redundant research work and encourage knowledge sharing as the field rapidly evolves.. It aligns with his commitment to open science and community knowledge sharing.

Key Takeaways

I came away from our wide-ranging discussion with an insider’s view of the huge potential of image analysis to transform digital pathology. By leveraging open source tools and staying atop the latest advances, you can work smarter and unlock new capabilities.

So tune in to explore these innovations and more from a leader in the field! The episode provides practical insights you can apply to make the most of the newest techniques

THIS EPISODE'S RESOURCES:

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

77: ChatGPT Conundrum

27 oktober 2023 | 38 min

76: 12 Years of Digital Pathology Innovation and What to Expect Next w/ Kate Lillard Tunstall, Indica Labs

17 oktober 2023 | 41 min

The Future Landscape of Digital Pathology: Insights from Kate Lillard Tunstall, Indica Labs

What insights can be gained from a 12-year-long digital pathology journey as part of one of the leading tissue image analysis solution providers? A lot has happened in that time and Kate Lillard Tunstall, the Chief Scientific Officer at Indica Labs, shares her vast knowledge and experiences in this podcast episode. With a career spanning over a decade, Kate has witnessed firsthand the transformative shifts in the industry.

The Genesis of Halo:

Kate reminisced about the early days of Indica Labs and the birth of their core product, the Halo platform. Designed with precision and adaptability in mind, Halo has become a beacon in the digital pathology and tissue image analysis landscape. The platform's name, inspired by the unique halo-like appearance around cells visible during image analysis, showcases Indica Labs' attention to detail and their connection to the core of pathology.

Services Beyond Software:

Indica Labs isn't just about software; they offer a plethora of services tailored to the needs of the pharma sector and beyond. Their pharma services team, which has been around the longest, acts as a bridge between product development and real-world application. By serving as an internal customer, this team ensures that Indica Labs' offerings are not only cutting-edge but also practical and user-friendly.

Embracing the AI Revolution:

The integration of AI into digital pathology was a significant pivot point for Indica Labs. Kate candidly shared her initial skepticism towards AI's role in pathology. However, witnessing the profound impact of deep learning, especially in tissue classification, turned her into a believer. By 2017, Indica Labs had fully embraced AI, setting itself apart in the industry.

Looking Ahead:

Kate's vision for the future is a world where digital pathology isn't the exception but the norm. As more hospitals and health systems go digital, the volume of data will skyrocket. This data surge, combined with the power of AI, promises unprecedented advancements in pathology. Kate also shared lessons from Strata, a project aimed at merging image analysis data with patient data. Spoiler alert - the project was not pursued, but the challenges it faced underscored the importance of innovation adaptability and a deep understanding of customer needs in the world of digital pathology.

----------------------------------------------------

Dive into the world of digital pathology and stay updated with the latest breakthroughs. Subscribe now!

For those eager to delve deeper, join the Digital Pathology Club and
secure your copy of the e-book "Digital Pathology 101"

----------------------------------------------------

#DigitalPathology #PathologyInnovations #IndicaLabs #AIRevolution #Halo #FutureTrends

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

73: Digital Pathology 101 Chapter 3 | Image Analysis, Artificial Intelligence, and Machined Learning in Pathology

16 oktober 2023 | 53 min

Image analysis has supported pathology since the introduction of whole slide scanners to the market, and when deep learning entered the scene of computer vision tissue image analysis gained superpowers.

There are regulatory compliant AI-based image analysis tools available for practicing pathology around the globe.

So what shall you do, just embrace them and start using?

I would learn a bit about image analysis and AI first, to be able to make an informed decision.

Good news, you can get all the information needed for this informed decision from this very chapter of the "Digital Pathology 101" book that I have published for you.

From Chapter 3 you will learn the fundamentals of tissue image analysis and how it helps extract meaningful data from digital pathology images.

We break it down into basic concepts like

regions and objects of interest,
matching computer vision techniques to pathology tasks, and the
differences between classical machine learning and AI-based deep learning approaches.

Understanding these foundations sets the stage for appreciating how image analysis is applied in regulated clinical settings versus exploratory research environments. You will learn the importance of quality control, because flawed data inputs inevitably lead to faulty outputs, regardless of the analysis method used.

Moving on, you will familiarize yourself with the key terminology from the world of artificial intelligence and machine learning.

The chapter clarifies the meaning of concepts like

supervised learning,
GPUs,
data augmentation, and
heat maps.

It emphasizes how techniques like

patching and
data augmentation

enable the training of machine learning algorithms on large datasets.

Ultimately, by comprehending this terminology and the basics of tissue image analysis, you'll gain clarity on how these tools can provide decision support to pathologists through computer-aided diagnosis. Rather than seeing AI as a black box, you'll have insight into how it arrives at its outputs.

With this balanced understanding, you'll be equipped to make discerning choices about embracing AI tools in your pathology practice, leveraging their benefits while being aware of current limitations.

Stay tuned as we continue unpacking the transformative potential of digital pathology!
Talk to you in chapter 4!

-------------------------------------------------------

Get the paper copy of "Digital Pathology 101" on AMAZON

Watch the "Digital Pathology 101" Book Launch here

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

74: Digital Pathology 101 Chapter 4 | Digital Pathology Applications

16 oktober 2023 | 31 min

Get the PDF of "Digital Pathology 101" Book here

Have you started your digital pathology journey already?

Chances are that if you are reading this, you have. You have started it in a particular point of "digital pathology entry". Maybe it was tissue image analysis, virtual rounds on whole slide images or validation of a scanner.

My "digital pathology entry point" was tissue image analysis and only through the lens of this application have I learned what are the other digital pathology applications.

In this chapter you will learn about all the current applications of digital pathology.

Because of where I started my journey I will always be biased towards tissue image analysis and AI, but revisiting the overview provided in this chapter will help me have all the other applications in mind, when I continue my journey of promoting digital pathology in the scientific and medical community.

I hope it will be a good basis for you as well. So let's dive into the contents.

Here is what you will learn in Chapter 4 of the "Digital Pathology 101" book:

We'll start by looking at the clinical applications. This includes

the use of digital pathology for primary diagnosis in surgical pathology and cytopathology.

It facilitates more detailed examination and collaboration between pathologists. We'll also discuss

how telepathology enables remote intraoperative consultations and second opinion consults.

And we'll touch on the

education and training benefits, from resident teaching to continuing medical education.

Moving to research, we outline key applications like

quantitative image analysis,
AI and machine learning for predictive modeling, and
high throughput analysis.
collaboration, allowing researchers to simultaneously access images
large scale studies and validation across institutions.

In drug development, digital pathology enhances

preclinical histopathology and
biomarker evaluation
clinical trials by eliminating slide shipment and enabling centralized review.

Digital tools can also assist in developing companion diagnostics, although regulatory requirements here are still evolving.

While each application has its challenges, the overarching benefit of digital pathology is its

capacity to connect workflows,
enhance efficiency, and
open new possibilities across clinical, research, and drug development spheres.

Understanding the breadth of these applications provides a compass for navigating our own digital pathology journeys.

Enjoy this chapter and I'll talk to you in chapter 5.

-------------------------------------------------------

Get the paper copy of "Digital Pathology 101" on AMAZON

Watch the "Digital Pathology 101" Book Launch here

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

75: Digital Pathology 101 Chapter 5 | The Role of Whole Slide Imaging in Toxicologic Pathology

16 oktober 2023 | 10 min

Toxicologic pathology plays a critical role in drug development, yet its intersection with digital pathology is often overlooked. As a veterinary pathologist, I want to shed light on this important application.

This is Chapter 5 of the "Digital Pathology 101" book and in this chapter, you will learn how whole slide imaging is transforming preclinical trials. I'll explain key concepts like creating faithful digital replicas of glass slides. We'll also dive into validations needs for digital systems in regulated GLP studies.

Whole Slide Imaging Overview

I'll start by explaining whole slide imaging. This technology creates 2D digital copies of glass slides. The focus is not 3D images, but flat digital images containing the visual information pathologists need for analysis and reporting.

The FDA states these digital images can substitute for glass slides in preclinical toxicity studies, provided they meet requirements as "faithful digital replicas." With proper validations, digital slides enable remote assessments for multisite trials.

Validation and Documentation

For regulated GLP studies, replacing glass slides necessitates validating the whole digital pathology system. This includes IT infrastructure, scanners, software and more based on intended use.

Documentation is also key. Peer review statements should note the use of digital slides. Images must be securely stored and transmitted to maintain raw data integrity.

Conclusion

In closing, the FDA's guidance on digital pathology in preclinical trials signals an important step towards regulatory acceptance. Digital tools promise more controlled, efficient toxicity assessments, ultimately advancing drug development.

This chapter provides a compass for teams navigating digital pathology in regulated environments. Understanding principles of validation, security, and transparency allows us to realize the benefits while ensuring high standards.

You can find the original FDA guidance document this chapter is based on here:

Use of Whole Slide Imaging in Nonclinical toxicology Studies: Questions & Answers.

Or you can watch me explain the guidelines here:

What does the FDA Say About Digital Pathology for Nonclinical Toxicology Studies?

-------------------------------------------------------

Get the paper copy of "Digital Pathology 101" on AMAZON

Watch the "Digital Pathology 101" Book Launch here

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

72: Digital Pathology 101 Chapter 2 | Challenges and Benefits of Digital Pathology

16 oktober 2023 | 43 min

Get the PDF of "Digital Pathology 101" Book here

As enthusiastic as the digital pathology community is about digital pathology, you are also grounded in reality and know that like every technology, digital pathology in parallel with its enormous benefits also has some drawbacks.

This is the second chapter of the "Digital Pathology 101" book and in this episode, I take a balanced look at the pros and cons of going digital.

Benefits

First, we highlight some of the key advantages:

enhanced accuracy and efficiency in diagnostics,
seamless collaboration opportunities,
advanced research capabilities,
integration with digital health systems, and
exciting educational prospects.

Real-world examples showcase how these benefits have been leveraged, like the successful implementation of digital workflows in a large US hospital and the application of digital pathology in pharmaceutical research.

Challenges

However, we acknowledge this new frontier has its challenges. Technological hurdles around

image quality,
data storage, and management are significant.
Navigating regulatory compliance and
acceptance within the pathology community will take time.
Cost-efficiency and specialized training remain issues to tackle.

Yet for each obstacle, there are solutions and opportunities to learn. Case studies teach us how institutions overcame cost barriers through long-term planning and addressed training needs via technology partnerships.

Constant advances promise more efficient scanning and sophisticated cloud storage on the horizon. And an evolving regulatory environment is steadily validating digital tools, albeit with a need to standardize guidelines.

While adoption is uneven, momentum is building towards digitization. By understanding the landscape and staying engaged with developments, pathologists can shape an ethical integration of these tools. Guided by both optimism and pragmatism, we can realize the potential of digital pathology to transform patient care.

-------------------------------------------------------

Get the paper copy of "Digital Pathology 101" on AMAZON

Watch the "Digital Pathology 101" Book Launch here

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

71: Digital Pathology 101 Chapter 1 (Part 2) | Are Pathologists at Risk in the Digital Age?

11 oktober 2023 | 21 min

This is the second part of the first chapter of the recently published “Digital Pathology 101” book.

This part of the chapter addresses a question that I keep hearing from those just entering the world of digital pathology: “Will pathologists lose their jobs now, that algorithms can be developed to diagnose disease?”

The short answer is “No”.

Keep reading for the explanation why not.

The Rise of Deep Learning

One of the most notable trends has been the rise of deep learning and AI in digital pathology. These advanced techniques are being embraced by the pathology community to analyze complex issues from sclerotic glomeruli through liver fibrosis to different types of cancer. The user-friendliness of new tools powered by deep learning makes it accessible even for non-experts.

Industry Paradigm Shifts

Several paradigm shifts are occurring in the digital pathology industry:

Transition from handcrafted algorithms to deep learning
Shift to cloud-based Software as a Service (SaaS) solutions
Movement towards pathologist decision support systems rather than fully autonomous analysis
Enhanced user-friendliness of digital pathology software

Empowering Pathologists

An important change has been the emphasis on empowering pathologists with decision support systems rather than replacing them with algorithms. The goal is to accelerate the case review process without compromising accuracy or integrity. Pathologists remain responsible for the final diagnosis.

Blending Analog and Digital Worlds

Some innovative companies are pioneering solutions to blend traditional microscopes and digital pathology, such as Augmentics' augmented reality microscope cameras or systems used by Smart in Media. This allows professionals to collaborate in real-time and apply algorithms while still using the cherished microscope.

Personalized Digital Pathology

The industry has moved away from a one-size-fits-all approach to personalized solutions tailored to each institution's workflow and challenges. This shift leverages the power of deep learning while enhancing user experience.

The trusted microscope remains an essential part of pathology, but digital solutions open new doors for analysis and efficiency. As this field evolves, quality control and understanding the capabilities and limitations of technology is crucial.

Exciting times are ahead in digital pathology! Be sure to listen to the full podcast episode for an in-depth discussion.

-------------------------------------------------------

Get the paper copy of "Digital Pathology 101" on AMAZON

Read the original blog post "New Trends and Paradigm Shifts in the Digital Pathology Industry"

Watch the "Digital Pathology 101" Book Launch here

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

70: Digital Pathology 101 Chapter 1 (Part 1) | Digital Pathology Milestones and Basic Digitalization Concepts

10 oktober 2023 | 51 min

Get the paper copy of "Digital Pathology 101" on AMAZON

I'm thrilled to introduce you to a long-awaited companion in your digital pathology voyage – the book, "Digital Pathology 101 - All you need to know to start and continue your digital pathology journey."

This book is the culmination of months of passion and hard work. If you've been following me on social media, you know it's been a labor of love. But why did I write this book, you might ask? Well, it's your comprehensive guide to navigating and thriving in the realm of digital pathology.

But first, let's rewind a bit. Back in 2003, Dr. Anil Parwani predicted that everyone would be digital by 2007. Well, that might have been a bit too optimistic, but guess what? The digital age in pathology is here, and it's not a distant future; it's right around the corner.

I'm convinced that now is the time, and that's why I'm so excited to share this book with you.

If you missed our webinar launch, don't worry – you can catch the replay here .

In that webinar, I delved deep into why digital pathology is the future, and trust me, it's a future you don't want to miss out on.

But enough about that, let's dive into the first chapter of the audio version of "Digital Pathology 101." In this chapter, we'll explore the historical milestones that paved the way for digital pathology. So, without further ado, let's get started on this journey into the world of digital pathology.

Here is what we will cover in this part of chapter 1:

DIGITAL PATHOLOGY MILESTONES

A. Historical Milestone
B. Regulatory Milestone

BASIC DIGITALIZATION CONCEPTS

A. About Digitization, Digitalization and Digital Transformation
B. Digitization - The Scanner and its Components
C. Digitalization and its challenges - Data Generation and Management
D. Digital transformation: Advantages and Challenges of Digital Pathology

--------------------------------------------------------------------------------------

Get the paper copy of "Digital Pathology 101" on AMAZON

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

69: How to Set Realistic Expectation in Digital Transformation w/ Anil Parwani, Ohio State University

4 oktober 2023 | 34 min

In this episode of "The Digital Pathology Podcast," we delve into the fascinating career of Dr. Anil Parwani from Ohio State University, a visionary whose ardor for technology and research paved the way for groundbreaking advancements in digital pathology.

Dr. Parwani's journey commenced with a bold move – launching a web educational series during his residency – well ahead of digital pathology's mainstream emergence. As we delve into his narrative, you'll witness how his pioneering spirit laid the groundwork for a transformative trajectory. The pivotal moment? It arrived with the debut of the first digital pathology scanners. Dr. Parwani envisioned a future where patient care and pathology research could soar to unprecedented heights through digitization. His role in implementing digital pathology solutions, including collaborations with startups, deepened his grasp of the clinical significance of this game-changing technology.

As the COVID-19 pandemic accelerated technological advancements in digital pathology, Dr. Parwani witnessed a significant 20% surge in adoption within his institution. How did they strike the ideal balance between remote and in-person interactions? Discover the insights in this episode.

Furthermore, in an era where the number of medical students pursuing pathology is dwindling, we'll examine how digital pathology is sparking renewed interest. Dr. Parwani reveals how this field, with its research prospects, educational promise, and collaborative ethos, is reshaping perceptions and attracting fresh talent.

Stay tuned for an expedition through the dynamic realm of digital pathology with Dr. Anil Parwani. It's a captivating odyssey into innovation, precision, and the future of medical science that promises not to disappoint!

Start your 7-day free trial: Digital Pathology Club Membership

EPISODES YOU WILL ALSO ENJOY:

DIGITAL PATHOLOGY RESOURCES:

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

68: The Evolution of Digital Pathology: 2013 vs. 2023 w/ Dr. Matthew O. Leavitt, DDx Foundation

20 september 2023 | 56 min

67: What Is the Role of Digital Pathology in Clinical Trials w/ Monika Lamba Saini

29 augusti 2023 | 29 min

How is digital pathology used in clinical trials? Because digital pathology as a discipline began with the aim of streamlining clinical trials, one could assume that this is currently the default.
Unfortunately, this is not the case… In today's discussion, our guest, Dr. Monika Lamba, a pathologist from Q2 Solutions, the lab division of IQVIA, sheds light on how digital pathology revolutionizes the landscape of clinical trials but also where we can still see the gaps.

In this engaging conversation, we discover how the origins of telepathology marked the inception of digital pathology and its journey to becoming an essential component of clinical trials.
Dr. Lamba walks us through the complexities of clinical trials, their organization, and patient matching across multiple sites and international boundaries.

As we unravel the role of pathology in clinical trials, we delve into how eligibility criteria, participant engagement, and informed consent are intricately woven into the process. Dr. Lamba educates us on the critical role of pathology in stratifying and randomizing patients, as well as evaluating outcome measures.

From disease staging to pathologic complete response assessments, pathology guides the way toward precision medicine and targeted therapies. Don't miss this captivating episode where we explore the synergy between digital pathology and clinical trials, paving the path for medical advancements and transformative healthcare solutions. Tune in now to expand your horizons on the ever-evolving intersection of digital pathology and clinical trials.

Start your 7-day free trial: Digital Pathology Club Membership

EPISODES YOU WILL ALSO ENJOY:

DIGITAL PATHOLOGY RESOURCES:

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

66: What You Need to Know About Digital Pathology Trends: Takeaways from the DP & AI Global Engage Event with Giovanni Lujan

2 augusti 2023 | 21 min

65: What Is Translational Research In Digital Pathology? /w Anant Madabhushi, Emory University & Georgia Tech

6 juli 2023 | 51 min

64: How To Overcome Challenges In Image Analysis For Spatial Biology w/ Lorenz Rognoni, Ultivue

8 juni 2023 | 21 min

Exploring Spatial Biology and Image Analysis with Lorenz Rognoni

Get ready for a deep dive into spatial biology and image analysis with Lorenz Rognoni, the Director of Image Data Science at Ultivue. Ultivue is a company specializing in spatial biology and Lorenz brings his wealth of knowledge in multiplex immunofluorescence (mIF) and image data science to this great conversation.

Multiplex IF: Challenges and Complexities

We kick off our discussion by addressing the inherent challenges in multiplex IF. The conversation spans a range of issues including tissue preparation artifacts, unique tissue morphology, and antibody-specific staining. The vast variability of tissues, differing across body regions, species, and health conditions, is a recurring theme. We also delve into the effectiveness of expert visual evaluation for traditional stains and the need for new strategies to interpret high-dimensional data.

Brightfield Imaging in Spatial Biology: Does it Still Play a Role?

Shifting gears, we discuss the role of brightfield imaging in spatial biology. Is there still space for brightfield if we want to learn the spatial interactions of cells in the tissue? Is this method not too limiting?
Lorenz underscores its continued relevance, particularly when robustness and scalability are prerequisites. He suggests transitioning to simpler methods like singleplex IF or even brightfield imaging, once research zeroes in on specific biomarkers of relevance with multiplex IF.

Transitioning from Image Analysis to Data Interpretation: Navigating the Pitfalls

Our conversation culminates in a look at the challenges and potential missteps in moving from image analysis to interpreting the data generated. Lorenz points out the crucial process of extracting meaningful insights from millions of cells, defining appropriate phenotypes, and considering the intricacies of downstream data mining.

Key Takeaways

mIF is an exploratory method and the insights gained can later be transitioned ti simpler methods such as single market IF or IHC
The spatial biology research relies on accurate cell segmentation and identifying the correct phenotypes of cells.
Correct segmentation is the first step to explore the insights and this exploration is being done through informed data mining that takes into consideration all the information about the study. This is best done by an image data science team where image analysis scientists, data mining experts and pathologists work together.

Join us for this insightful conversation and gain a deeper understanding of the complexities and nuances of spatial biology and image data science with Lorenz Rognoni.

Keywords: Lorenz Rognoni, Ultivue, spatial biology, image analysis, multiplex immunofluorescence, tissue morphology, brightfield imaging, data mining

THIS EPISODE'S RESOURCES:

Lorenz Rognoni on LinkedIn
Ultivue Official Website

DIGITAL PATHOLOGY PLACE RESOURCES:

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

63: Is this the year of AI in pathology? And what about ChtGPT? A crossover podcast with Beyond the Scope.

24 maj 2023 | 34 min

62: Changing Stereotypes of Pathology. How Pathologists Contribute to Patient Care w/ Marilyn Bui, Moffitt Cancer Center

2 maj 2023 | 36 min

61: The best online pathology book ever w/ Nat Pernick, PathologyOutlines.com

17 april 2023 | 25 min

Introduction
Are you curious about what goes into creating a cutting-edge digital online resource like PathologyOutlines.com? Then this episode is for you!

About PathologyOutlines.com
PathologyOutlines.com is a living textbook that covers 4,800 topics and involves 300+ contributors and 60 editors. It's a comprehensive online pathology resource that provides invaluable information for anyone in the pathology space.

PathologyOutlines.com Peer Review Process
The PathologyOutlines.com team takes great pride in their accuracy and responsiveness, as evidenced by their peer review process and willingness to address typos and other errors brought to their attention by users immediately.

Contributing to PathologyOutlines.com
PathologyOutlines.com is seeking contributors who are willing to submit their own images and articles to the website. This is a fantastic opportunity for anyone in the pathology field who is looking to expand their online portfolio and make a valuable contribution to the industry.

Personal Profile on PathologyOutlines.com
PathologyOutlines.com offers the chance to create a mini personal page on their website. This is a great opportunity for anyone practicing pathology in the world to be featured in the PATHOLOGIST DIRECTORY.

IHC Stains and CD Markers Explained
The page with all the IHC stains and CD markers explained is a favorite resource of many pathology professionals. This is an invaluable resource for anyone working in the IHC quantification space.

Digital Pathology Starter Kit
For those just starting their journey in digital pathology I have a special gift - the Digital Pathology Starter Kit. It contains valuable resources and information to help you get started on your digital pathology journey. This includes tips on how to choose a scanner, recommendations for digital pathology software, and much more.

Keywords: digital pathology, pathology professionals, PathologyOutlines.com, online pathology resource, peer review process, contributors, IHC stains, CD markers, digital pathology starter kit, personal profile.

THIS EPISODES RESOURCES:

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

60: End-to-End Solution for Digital Pathology w/ Leif Honda, TriMetis Life Sciences

10 april 2023 | 49 min

In digital pathology is it best to start small and incrementally implement the technology or go all in to reap all the the benefits at once?

The good news is that those two approaches are not mutually exclusive, you can totally start small and scale up, and you can do it with just one vendor partner if you feel like it!

This episode's guest is Leif Honda, Chief Innovation Officer at TriMetis Life Sciences. TriMetis is a unique company that serves as an external hub for those who want to start digital pathology but do not have all the components.

In an ideal world, going all-in would be the best option, but due to the high costs, it may be better to start small and work with partnering companies to take advantage of the full infrastructure and TriMetic can help with that.

Leif has an extraordinary background - he has a molecular biology and economic degree. This combination positions him perfectly to be the Chief Innovation Officer.

TriMetis started as a biobank, and started leveraging digital pathology to digitize the H&E slides of their biobank samples. Later they started using image analysis to quantify the amount and type of tissue present in their biobanking samples. Then they offered this type of service to other biobanks and other research institutions.

They are on a mission to accelerate cancer research through facilitating access to the relevant bio-specimen for everyone who needs them. Currently they also enable the image analysis algorithm creators to deliver their algorithms to cancer researchers and deploy them through the TriMetis digital platform.

All these developments make TriMetis an End-to-End digital pathology solution for cancer researchers.

Listen to the full episode to learn more about how you can benefit from their work.

THIS EPISODE'S RESOURCES:

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

59: Top 5 Mistakes you must AVOID in using Machine Learning for pathology w/ Heather Couture, PixelScientia Labs

22 mars 2023 | 32 min

58: The Regulatory Aspect of Digital Pathology and Translational Medicine w/ Esther Abels

15 mars 2023 | 34 min

Today's podcast is about the regulatory aspect of digital pathology and how it fits into the space between research and clinical use called translational medicine.

The podcast guest, Esther Abels, is a regulatory expert in digital pathology and a female leader in the field. She was involved in the team effort that brought the first Phillips clearance of a whole slide scanner to the attention of the FDA.

Translational research has the potential to bridge the gap between discovery and clinical practice. Its goal is to use evidence from research to target diseases and apply the insights in the clinic.

Digital pathology is seen as a tool to expedite the development pipeline for drugs and medical devices through the use of algorithms and AI.

There are however regulatory requirements that need to be taken into consideration when developing and using digital pathology tools. For example tissue image analysis tools used to support clinical decisions need to adhere to the FDA's guidance for software as a medical device.

The FDA is also working to define data sets that can be validated and reused for algorithm development.
There are ongoing efforts in Europe and the US to draft laws and frameworks related to artificial intelligence and validation techniques for AI tools.

It is a best practice to engage with the FDA early and this process for drug and medical device companies starts with a pre-submission to the FDA, seeking advice and discussing the approach. To be successful the role of a regulatory architect is crucial in overseeing the process and guiding it from point A to B to Z.

In addition to being a regulatory expert in the digital pathology field, Esther is also the immediate past president of the Digital Pathology Association (DPA). Because digital pathology brings people together from various fields, including pathologists, toxicologists, lab personnel, regulatory experts, and clinical development personnel, during her presidency Esther focused on collaboration between those different fields.

Esther Abels is a regulatory consultant who can be found on LinkedIn and her YouTube channel, which features helpful guidance and information videos.

THIS EPISODE'S RESOURCES:

✔️ Previous podcast with Esther: REIMBURSEMENT FOR DIGITAL PATHOLOGY IN THE CLINIC – HOW DOES THAT WORK? W/ ESTHER ABELS, VISIOPHARM
✔️ FDA GUIDANCE - CLINICAL DECISION SUPPORT SOFTWARE
✔️ FDA GUIDANCE - SOWTWARE AS A MEDICAL DEVICE
✔️ FDA GUIDANCE LIST FOR DIGITAL HEALTH
✔️ Beyond the Scope Podcast "CPT Coding and Digital Pathology Reimbursement"
✔️ ESTHER ABELS LINKEDIN
✔️ ESTHER ABELS YOUTUBE

💻 Bridging the Gap Between Pathology and Computer Science

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

57: Beyond innovation - how to embrace responsibility and leadership in digital pathology at a personal and national level w/ Inti Zlobec

8 mars 2023 | 35 min

Today is the International Women's Day and this month at the Digital Pathology Podcast I decided to invite some incredible women who are leaders in the digital pathology field.

Today's guest, Inti Zlobec is a professor of Digital Pathology at the University of Bern. Inti is now leading the digital pathology branch of the Institute for Tissue Medicine and Pathology, where she bridges the gap between pathologists, computer scientists, and data scientists. She also serves as the president of the Swiss Digital Pathology Consortium. The institute's name was changed to emphasize the dynamism in pathology and its links to various other domains.

Her background is in statistics and computational research combined with a PhD in experimental pathology at the University of McGill in Canada. Combining and hybridizing those two fields has been a blessing for her in bringing people with different backgrounds together. Bothe her background and personality make here a natural connector of all digital pathology links.

A crucial part of this linkage is removal of the intimidation factor associated with pathologists. Instead the focus should be on acquiring the necessary level of knowledge for collaboration. It's important to involve pathologists in the projects early and give them them a sense of contribution to foster a productive collaboration.

Pathologists should not just be used for annotations and quick checks, but should be included in projects as equal contributors.

In addition to Inti's University appointment she also is the president of the Swiss Digital Pathology Consortium (SDPath).

In 2018, a group of three professionals (Inti included:) in Switzerland founded the Swiss Digital Pathology Initiative (SDPI) to promote digital pathology and exchange knowledge. The initiative grew to over 140 members, and in 2021, SDPI collaborated with the Swiss Personalized Health Network to build a digital pathology network across Switzerland.

The goal of SDPI is to harmonize and structure data by scanning cases, attaching a minimum set of variables to images, and using standardized hardware and formats. This network will allow researchers and industry partners to access virtual cohorts of patients for clinical trials, and the harmonized data sets can also help boost pharmaceutical development.

This would be the first initiative of this kind at a national level which will create a fantastic model for others to tweak and follow.

As a female in science in general and in the digital pathology field specifically, she has been fortunate to be surrounded by people who value her ideas and ideas of others, regardless of their gender. The gender gap in this field is still noticeable, particularly in more senior positions, which affects the number of female role models. Often insecurity can prevent some women from advancing, but exposure, experience and dedicated work on overcoming your own limitations will help. And so will involvement in initiatives such as SDPI.

THIS EPISODE'S RESOURCES:

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

56: The beginnings of computational pathology w/ Jeroen van der Laak, Radboud UMC

21 februari 2023 | 26 min

Computational pathology – how did this field even start?

In today’s episode my guest is Jeroen van der Laak, computational pathology professor at Radboud University Medical Center, who was recently listed on "The Pathologist Power List" in the category “Strange New worlds”

Jeroen has been in the field of computational pathology for over 30 years and has seen it being created and evolve.

He witnessed how advancements in whole-slide imaging and deep learning have allowed for the practical application of AI in pathology.

Throughout the evolution of the field of computational pathology the focus has shifted from research-oriented work to direct collaboration with clinicians to test AI in diagnostic practice.

During his tenure Jeroen has seen what it takes to be successful in the field of computational and digital pathology.

To be a successful researcher in this field you need to understand the importance of high quality data and understand how the field of pathology works and what you see in the tissue you are analyzing.

This is a very collaborative field and a responsibility of an AI researcher is making AI accessible and breaking down technical aspects for pathologists.

Jeroen co-leads the Computational Pathology Group at Radboud with two other researchers – Francesco Ciompi and Geert Litjens. Their criteria for choosing successful candidates for a digital pathology group include good team spirit, collaboration, willingness to learn, and understanding of the field.

It is just a matter of (not too much) time when AI will become mainstream in pathology labs and will improve the accuracy and speed of patient diagnosis. Just like whole slide scanning is becoming part of the routine pathology workflow, so will AI based image analysis.

THIS EPISODES RESOURCES

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

55: Merging hardware and software to deliver 2nd generation digital pathology w/ Prasanth Perugupalli, Pramana

31 januari 2023 | 36 min

54: Cytomine - a free the tissue image analysis tool for all: pathologists, developers and the lab w/ Gregoire Vincke, Cytomine

22 januari 2023 | 51 min

53: Why digital pathology will be mainstream soon w/ Aleksandra Zuraw, Digital Pathology Place

29 december 2022 | 8 min

I started working in the digital pathology space, because it sounded cool.

When I started my digital pathology journey in 2016 as the first full time pathologist supporting the image analysis team, I thought it was the coolest job to get straight out of my veterinary pathology residency!

I was regarded as an expert (such a different feeling from what you experience during your training, when you are constantly being reminded how little you know and how much there still is to learn), which increased my confidence and motivated me to learn more. After all I needed to explain pathology to computer scientists.

Working together with the image analysis team and the software development team was exciting and I got to play and test software to view and annotate images.

Yes...
⛌ The images were shipped on hard drives
⛌ It took forever to open an image (over 30 sec...sometimes several minutes)
⛌ The annotation tool would regularly crash

FAST FORWARD 6 years

✔️No more hard drive shipping
✔️The speed of working with digital slides matches my speed at the microscope
✔️I didn't have to reboot my computer a single time today
✔️I work entirely remotely and can attend all recitals and events my kids take part in

VERY SELFISHLY I WOULDN'T WANT TO HAVE IT ANY OTHER WAY

I know I'm part of a minority of privileged pathologists. But it very much reminds me of the time when smartphones came to the market, when I could not afford one yet and they did not have so many functionalities

I was dreaming of having one that could always connect to the Internet, so that I could use Google Maps whenever I wanted (both on vacation and during my commute as a Polish PhD student studying in Germany - knowing the fastest way home on the weekend and avoiding traffic would be priceless!)

NOW EVERYONE HAS A SMARTPHONE

And would you want to have a different phone? The old one?
I know some would, but THEY ARE A MINORITY NOW.

How far are you in your digital pathology journey?
How do you feel about it? Is it already a reality or still a science fiction for you?
Let me know in the comments on LinkedIn

THIS EPISODE'S RESOURCES:
Digital Pathology Starter Kit + Digital Pathology Newsletter
"I started because it was cool..." - LinkedIn post

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

52: What does the FDA say about non-clinical digital pathology for GLP?

20 december 2022 | 27 min

51: What should we fix in digital pathology with Puneet Pantane, Crosscope

30 november 2022 | 26 min

50: How to approach colon cancer with supervised deep learning image analysis w/ Rish Pai, Mayo Clinic

21 november 2022 | 34 min

49: Scaling up your digital pathology operations with Mark Zarella, Mayo Clinic

8 november 2022 | 30 min

48: What the heck is DICOM in Pathology? w/ David Clunie, PixelMed Publishing

28 oktober 2022 | 43 min

47: Artificial Intelligence in Digital Pathology (a conference talk recording) w/ Aleksandra Zuraw

22 oktober 2022 | 29 min

46: Leveraging the power of static telecytology for veterinary diagnostics w/ Kate Baker

10 oktober 2022 | 51 min

45: What's up in Digital Pathology - a crossover podcast with Beyond the Scope

16 september 2022 | 35 min

44: Weakly supervised AI for pathology w/ Geert Litjens, RadboudUMC

28 juli 2022 | 53 min

43: Never miss a piece of digital pathology knowledge ever again! Digital Pathology Place and Pathology News partnership w/ Jonathon Tunstall

5 juli 2022 | 22 min

There are a few websites online other than the Digital Pathology Place that talk about different aspects of digital pathology. An important one being Pathology News.

Pathology News is an online place bringing together the digital pathology vendors and purchasers. It is meant to be a single community for everyone working in the digital pathology space. A community working together on advancing the digital pathology science.

A unique (and my favorite!) feature of the website, NOT AVAILABLE ANYWHERE ELSE ONLINE, is a special page where digital pathology users have access to detailed information about available digital pathology solutions provided by the digital pathology vendors.

It is like a 24/7 online digital pathology conference where the users can visit vendor space any time they need a specific piece of information, and they can visit multiple vendor spaces and compare their solutions.

All from the comfort of their home without having to call or interact with a single vendor representative before they are ready.

This space is called the Technology Buyers guide.

In addition to this unique vendor-purchaser interactive tool Pathology News has other elements:

- scientific articles
- latest digital pathology news
- list of upcoming digital pathology events
- digital pathology career section with the latest vacancies

and now also...[drum roll please]......

A PODCAST SECTION with the DIGITAL PATHOLOGY PODCAST

We partnered to serve the largest audience possible

Digital Pathology Place and Pathology News are both on a mission to advance digital pathology in the scientific community and we want to serve the largest audience possible. We are doing it in a very complementary way that builds bridges within the multidisciplinary environment of digital pathology.

This is why we partnered to make the Digital Pathology Podcast available to the Pathology News readers straight from the Pathology News website and from their mailbox for those who are subscribed to the monthly newsletter.

Listen to the full episode to meet Jonathon Tunstall, the CEO of Pathology News and learn what else you can find on the website.

This episode's resources:

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

42: BigPicture - the largest whole slide repository for AI model development in pathology. Where do we stand at month 15/72?

17 juni 2022 | 37 min

41: Digital Pathology for Dermatologists. How Pathology Watch managed to incorporate digital pathology in dermatology practices across the US w/ Dan Lambert, Pathology Watch

25 april 2022 | 23 min

Digital pathology is supposed to help pathologists provide better patient care and make their lives easier, but what about other doctors, do they even care? Maybe radiologists? Oncologists? Nope…Dermatologists! They do care!

And they are the clients of Pathology Watch – a CLIA lab specializing in dermatopathology, that is currently servicing samples from over 65 dermatology clinics in the USA.

Pathology Watch provides an end-to-end digital pathology solution for dermatologists. From processing the samples sent by the dermatologists, through the dermatopathology report to the whole slide image of the diagnosed sample, and all this browser-based and integrated with the dermatology clinic’s electronic medical record (EMR) systems. This provides a completely non-disruptive workflow.

Pathology Watch is providing a true end-to-end solution built around dermatologists.

The EMR integration saves the dermatologists time (25h/ month!!! Who would not want to have that?!?) and whole slide images build the bridge between and improve the communication on the “patient-dermatologist-pathologist” line.

Dermatologists can show the images of the cases to the patients, and they can see the highlighted areas used by the pathologist when diagnosing the case.

Once the digitization and intersystem integration take care of the time savings it’s time to step up the game! The next step is using artificial intelligence for better dermatopathology diagnostics and to gain even more time savings. Pathology Watch designed its AI pipeline specifically to bypass the known industry problem of generalizability of AI models.

It is extremely difficult to train generalizable models on samples from different institutions, but if the samples are processed in just one lab in a very controlled environment, using automated equipment and performing rigorous quality control, the pre-analytical variability causing a lack of generalizability is taken care of.

As in any digital pathology operation, troubleshooting is part of the business. What do you do when your scanner breaks down? How do you store the digital pathology images effectively in a cost-efficient way? And how do you deliver the slides in the browser FAST?

It took the Pathology Watch team a few years to solve those and other challenges and come up with good mitigation strategies.

Do you want to know how they did it? Listen to the full episode to learn more from Dan Lambert, the CEO of Pathology Watch.

This Episodes resources

Pathology Watch website

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

40: A simple microscope camera, whole slide scanner and everything in between. The different tiers of digital pathology w/ Mike Miller, I. Miller Microscopes

14 april 2022 | 34 min

A common misconception about digital pathology is that it is synonymous with whole slide imaging and has a high price point. This is not the case, as one can enter the digital pathology world and benefit from what it has to offer with a simple microscope camera. If we would like a more sophisticated solution, but don't want to get a whole slide scanner or don't have the use case or business case to justify it, no worries, there is enough to choose from!

In this episode, Mike Miller from I.Miller Microscopes is taking us through all the different levels and price points of digital pathology solutions from a simple microscope camera to a whole slide scanner explaining everything in between.

The digital pathology solutions discussed in this episode include:

Simple microscope camera + imaging software for image capture
- For teaching and learning
- For capturing static images
  - presentations
  - publications
  - tumor boards
- For screen sharing on communication platforms (e.g. zoom, teams, etc.)
Microscope camera with a network port allowing for live streaming
- For intraoperative evaluation by an on-site or off-site pathologist
  - fine-needle aspirates
  - frozen sections
Live remote control telepathology system
1. Live remote control telepathology system with low throughput screening capabilities (aka hybrid system)
  - For use in remote areas without access to pathologists
Whole slide scanners
- For high throughput digital pathology workflows on formalin-fixed paraffin-embedded (FFPE) material

Listen to the full episode to learn the details and the price points of each solution!

This episode resources:

I. Miller Microscopes website
Microscope central website
Path 4k - high-resolution microscope camera
- [DPP FAVORITE] Digital Pathology Place is a proud affiliate for the Path4K microscope camera, if you are interested in a quote, fill the form in the link and simply write in the message that you heard about it on our podcast.

Episodes you might also like:

Digital pathology in a suitcase. How Grundium's portable whole slide scanning microscope expands the reach of telepathology w/ Mika Kuisma, Grundium

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

39: How image analysis and artificial intelligence support digital pathology-enabled precision medicine today and what to expect in the future w/ Michael Grunkin, Visiopharm

15 mars 2022 | 20 min

This episode is brought to you by Visiopharm.

With the regulatory approvals of whole slide imaging systems, digital pathology became the modality for routine diagnostics. Digitalization of pathology is aiming at increasing precision and productivity in the pathology lab, but the adoption of this field is slower than expected.

One of the causes of the slow adoption is that going digital in a pathology lab means a much bigger investment than just the cost of the whole slide scanners for slide digitization. Additional costs include digital storage and infrastructure, slide and workflow management, and connectivity to lab information systems.

Because the improvements in precision and productivity gained by going digital are modest at best, a higher value is expected from image analysis and artificial intelligence.

The research and diagnostic applications of image analysis have been explored for decades already and many have found great use in the research-diagnostics continuum. However, a large need for the standardization of tissue diagnostic assays remains unmet.

Standardization of the staining and of the diagnostic interpretation of tests would tremendously benefit pathology and patient care. So far, the standardization efforts focused on the interpretation part of the puzzle. Several quantification algorithms have been developed, many of which received regulatory clearance. At the same time, the IHC assays on which the algorithms are based often lack standardization, and this is where more effort should be put.

Currently, only pathology institutions that go fully digital reap the digital pathology benefits. There is not an efficient way to start slowly, rather it seems to be “all or nothing”. Enabling institutions to embark on the digital pathology journey in an incremental fashion would change the digital pathology landscape and significantly increase the adoption of this technology.

The more value on different fronts digital pathology can provide to institutions and patients, the more the adoption will increase. And we have not yet explored all the ways in which value can be provided.

Listen to the full episode to learn about it in more detail and visit Visiopharm’s website, to learn how they are contributing to the digital transformation in pathology.

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

38: From digital microscopy to digital pathology through image analysis. How far have we come in 20 years? w/ Michael Grunkin, Visiopharm

8 mars 2022 | 19 min

Visiopharm is a company offering image analysis software used on pathology images. The software has been on the market for over 20 years and has evolved through the transition of digital microscopy to digital pathology. Digital microscopy provided static tissue images captured through the microscope camera and only branched out into digital pathology with the wider availability and adoption of whole slide scanners. Image analysis spans digital microscopy and digital pathology, and image analysis methods had to evolve in parallel with the imaging technologies to address the hypercomplex pathology problems.

The complexity of digital pathology problems and research questions increases with every additional stain and scientific discovery. Visiopharm’s team challenged themselves by providing an image analysis solution capable of addressing this hypercomplexity and enabling researchers to advance scientifically with their tool.

Artificial Intelligence (AI) capabilities applied to computer vision problems took tissue image analysis to a whole new level and incorporating AI into the Visiopharm software tremendously increased the accessibility of this method.

In addition to the two well-known technologies that enabled digital pathology breakthroughs (whole slide imaging and AI), two other important advancements happened during the last two decades

· emphasis on interoperability between different digital pathology systems

· advances in the field of data visualization.

Together these four components are driving the progress of digital pathology both on the diagnostic and research front.

During the last 20 years Visiopharm grew significantly, both organically and through funding and they continue creating value and powerful image analysis tools for the tissue image analysis community.

Listen to the full episode with Visiopharm’s CEO Michael Grunkin to learn more about this 20-year perspective on what happened in the field of digital microscopy and digital pathology.

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

37: How tissue clearing - based 3D immunofluorescence allows for seeing more biology in the tissue w/ Sharla White, ClearLight Biotechnologies

7 februari 2022 | 62 min

Even though tissues are tridimensional structures, most tissue research is done on two-dimensional tissue slides. This leaves a tremendous amount of biological information on the table. This episodes' guest - Sharla White, Ph.D., the vice president of research and development at ClearLight Biotechnologies explains how tissue clearing and 3D immunofluorescence can take your tissue research to a whole new level.

With the rise of immuno-oncology, the importance of immune cell interactions with the tumor cells is now routinely interrogated with immunofluorescent markers the spatial relationships of different immune cell populations are investigated. But how can we investigate something happening in a 3D space on a flat, two-dimensional tissue section? The truth is - in a very restricted manner. This is where tissue clearing and 3D immunofluorescence come into play.

The tissue clearing technology -CLARITY, developed by ClearLight Biosciences allows for maintaining the integrity of tissue and visualizing cells in their original place and shape at the same time by using 3D immunofluorescence.

In order to image deeper (beyond 100 micrometers), the light-scattering lipids of the tissue need to be removed and the refractive indexes of collagen, bone, and other tissue components need to be aligned. This is done after fixing the tissue and embedding it in a hydrogel. It ensures that the tissue structure is maintained before the detergent is applied to wash out the light-scattering lipids.

Once tissue clearing is done, antibodies with properties and in amounts compatible with the process are used for 3D immunofluorescence.

This powerful technology does not come without challenges such as:

the necessity of tissue bleaching for melanoma samples,
selection of appropriate immunofluorescence markers,
size of the 3D image files generated for visualization (often as big as 500 gigabytes reaching terabytes of data!)
meaningful interpretation of the results

Listen to the full episode to learn how Dr. White's team is approaching all the challenges, leveraging CLARITY potential and how this technology changes the way we do tissue research.

This episode's resources:

Episodes you might also like:

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

36: DICOM standard for pathology annotations. Why do we need it? w/ David Clunie, PixelMed Publishing

25 januari 2022 | 36 min

35: Digital veterinary cytology and social media teaching w/ Kate Baker, Veterinary Cytology Schoolhouse

11 januari 2022 | 42 min

In the world of anatomic digital pathology, the mention of digital cytology usually causes thoughts of all the challenges associated with it. We are often not aware that digital pathology and image analysis applications started with digital hematology and cytology (e.g. image analysis-based pap smear evaluation) and that in veterinary medicine digital cytology is a booming discipline.

Today’s episode’s guest, Dr. Kate Baker, is a board-certified veterinary clinical pathologist who has embraced the digital cytology journey even before she was doing diagnostic work on whole slide images.

Her digital pathology journey started with a Facebook group – Veterinary Cytology Coffee House where she started teaching veterinary cytology with static images. The group kept growing and reached sixty-two thousand members in January 2022. Group members kept asking for more digital cytology resources, so she created two RACE-approved courses for veterinary professionals and a monthly membership site – The Cytology Clubhouse. Currently, she does digital cytology on whole slide images in collaboration with a veterinary laboratory – Scopio.

Now confident with digital cytology images she remembers that there was a transition period when she needed her glass slides alongside the digital image to feel confident that she is not missing anything. As she experienced how the glass slides and the digital images consistently carry the same diagnostic information, she needed to consult the glass less and less until it was not necessary anymore.

The glass vs digital slide comparison is usually part of the digital pathology system validation and giving pathologists some time to adjust to the new modality with access to both digital images and glass slides during the adjustment period helps them gain confidence and be sure that they are still doing the best job possible.

Listen to the full episode to learn about Dr. Kate Baker’s digital cytology journey and explore her digital cytology educational resources:

Veterinary Cytology Facebook group – Veterinary Cytology Coffee House: Cases and Conversations
Website with all her veterinary cytology resources – The Veterinary Cytology Schoolhouse
The veterinary cytology membership site – The Cytology Clubhouse

And check her brilliant educational content on Instagram @clinpathkate.

And to gain more insights into the world of digital cytology listen to the podcast episodes below:

AI-powered digital diagnostic tools for medical, veterinary, and environmental laboratories w/ Ben Cahoon, Techcyte.

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

34: 5 ways to make histopathology image models more robust to domain shift w/ Heather Couture, Pixel Scientia Labs

29 december 2021 | 17 min

In this episode, we talk with Heather Couture about how to make deep learning models for tissue image analysis more robust to domain shift.

Supervised deep learning has made a strong mark in the histopathology image analysis space, however, this is a data-centric approach. We train the image analysis solution on whole slide images and want them to perform on other whole slide images - images we did not train on.

The assumption is that the new images will be similar to the ones we train the image analysis solution on, but how similar do they need to be? And what is domain and domain shift?

Domain: a group of similar whole slide images (WSI). E.g., WSIs coming from the same scanner or coming from the same lab. We train our deep learning model on these WSIs, so we call it our source domain. We later want to use this model and target a different group of images, e.g. images from a different scanner or a different lab - our target domain.

When applying a model trained on a source domain to a target domain we shift the domain and the domain shift can have consequences for the model performance. Because of the differences in the images the model usually performs worse...

How can we prevent it or minimize the damage?

Listen to Heather explain the following 5 ways to handle the domain shift:

Standardize the appearance of your images with stain normalization techniques
Color augmentation during training to take advantage of variations in staining
Domain adversarial training to learn domain-invariant features
Adapt the model at test time to handle the new image distribution
Finetune the model on the target domain

Click here to read Heather's full article on making histopathology image analysis models more robust to domain shift.

Visit Pixel Scientia Labs here.

And listen to our previous episode titled "Why machine learning expertise is needed for digital pathology projects" here to learn more about the subjects and learn how Heather and her company can help.

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

33: Smart in Media - the virtual microscopy hub w/ Martin Weihrauch MD, Smart in Media

14 december 2021 | 39 min

Advanced computer science expertise with the ability to code and a medical degree with over 20 years of clinical experience is a rare combination. This episode’s guest, Martin Weihrauch MD, the co-founder of Smart in Media incorporates this rare combination.

His digital pathology platform originated when he was asked by a pharmaceutical company to provide some interactive entertainment for the participants of a medical congress, something beyond just coffee, and the only thing really attracting participants to a company exhibition booth. He decided to host diagnostic quizzes with virtual microscopy. Since then, supported by the close collaboration of a pathologist, Dr. Alberto Peréz Bouza, the platform evolved from the initial virtual microscopy application, through a full pathology educational platform to a fully capable digital pathology diagnostic platform with an open API and the capability for AI algorithm integration.

Smart in Media is a digital pathology platform designed by physicians for physicians. The software is optimized for pathology workflow and IT infrastructure. Through the open API, it can communicate with any LIS or LIMS system, has the capability of image analysis algorithm integration, and is extremely user-friendly. Smart in Media users can give real-time feedback to the platform developers about any bugs or difficulties in a user WhatsApp group.

Smart in Media is already a leading digital pathology solution provider in Europe with its presence established in Germany, Austria, Switzerland, Italy, the UK, and the Czech Republic, and is the official digital pathology provider of the European Society of Pathology. With its presence expanding to the US the company is striving to bring digital pathology to every pathologist and to improve and speed up their workflow.

To learn more about Smart in Media visit their website here.

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

32: Why machine learning expertise is needed for digital pathology projects w/ Heather Couture, Pixel Scientia Labs

28 november 2021 | 36 min

What do cancer and climate change have in common? Both are very serious problems and in both, machine learning (ML) and artificial intelligence (AI) can be used to support potential solutions. Even though these AI applications may seem very different the ML methods used to support work on both problems are very similar.

Today’s episode’s guest, Heather Couture from Pixel Scientia Labs does exactly that – fights cancer and climate change with AI. She is a computer scientist specializing in computer vision machine learning and deep learning. She started her company during her Ph.D. when she was doing contract work and expanded her work after receiving her degree. She assists companies with accelerating their machine learning projects by distilling and adapting cutting-edge research and applying her over 16 years of experience in the field for analyzing images.

Not only does she stay on top of the current research herself, but she also posts about it on LinkedIn several times a week, extracting the most important and actionable information out of the most recent publications on machine learning applications in pathology.

Her consulting company gives her the opportunity to optimize her work for impact and get engaged with companies and projects that can really make a difference.

Teamwork is important in every area of life, but in the medical domain and especially in pathology it acquires a whole new dimension. No longer is it possible for a single observer to analyze the data in conjunction with the pathology images. The use of computer vision algorithms is often a must and to come up with medically and diagnostically relevant solutions the domain experts from pathology and computer vision need to work together.

In clinical settings and in medically focused companies machine learning expertise is necessary to leverage the power of artificial intelligence and apply it to their problems and challenges.

Heather supports her clients with such tasks as nuclear detection and classification, mitosis detection, segmentation of different tissue types in pathology images, stain normalization, and other techniques to enable a deep learning model to generalize images from a different scanner. All these things come into a lot of different projects, even if the project endpoints vary. Another important aspect of every deep learning project is data collection and data labeling.

Are you working with deep learning for pathology image analysis? If so, visit https://pixelscientia.com/ to learn more about the machine learning expertise you can leverage for your projects.

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

31: AI-powered digital diagnostic tools for medical, veterinary and environmental laboratories. How Techcyte uses AI for digital cytology and smears w/ Ben Cahoon, Techcyte

3 november 2021 | 42 min

AI-powered algorithms for digital pathology and tissue image analysis are not new, also digital cytology and hematology already have their share of AI algorithms helping pathologists with faster and more accurate diagnoses. But what about parasitology or microbiology? Techcyte has a tool for that as well.

Today my podcast guest is Ben Cahoon, the CEO of Techcyte, a software start-up that provides AI-powered diagnostic tools for everything smearable: fecal, blood, cytology, and microbiology smears.

Imaging specimen smears has all the challenges of digital cytology such as correct focusing, and then some more. This is why Techcyte's pipeline starts with optimizing the sample preparation for imaging through close collaboration with sample prep vendors, who then work with scanner manufacturers to ensure optimal image quality. Only then can data for model development be annotated.

Techcyte deep learning models specialize in the detection and classification of different structures such as blood cells, parasite eggs, and bacteria. The annotation process consists of placing bounding boxes around structures of interest to train the initial model followed by accepting or rejecting structures suggested by the preliminary model. This helps the model improve future predictions and in computer vision terminology is known as reinforcement learning. The images of the diagnostic samples are sent for analysis via a web browser and the results can be accessed there as well.

Techcyte's mission is to digitize and automate diagnostics through AI in order to minimize the cost of healthcare and the number of diagnostic mistakes. In the process of following their mission, Techcyte perfected the technique of fecal float imaging, which allowed them to penetrate and serve the production and companion animal market. In turn, this served as proof of concept and provides a revenue stream that enables the funding of further developments.

Their vision for medical diagnostics consists of five phases:

phase 1 is to automate an existing test such as a peripheral blood smear or fecal smear evaluation, to increase efficiency and recall;
phase 2 focuses on eliminating/ reducing the need for evaluation of the negative samples, which e.g., can constitute over 95% of fecal smears;
phase 3 would function as a diagnostic support tool presenting a diagnosis to the expert for confirmation;
phase 4 would enable the replacement of expensive tests such as flow cytometry with inexpensive image analysis tests
· and in phase 5 results of expensive and slow tests, for which microscopy is not the gold standard, such as PCR and sequencing could be derived from the image properties. This would eliminate costs and tremendously decrease the diagnostic turn-around time.

Reaching phase one will improve patient care significantly. Reaching phase five will revolutionize it.

This episode’s resources:

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

30: Microscope phone adapter that can bring digital pathology to everyone w/ Cade Wilson, Skoped Micro

18 oktober 2021 | 36 min

Buy the digital pathology kit for your phone here

This episode contains affiliate links. Learn what that means here

Have you ever tried to take a picture through your microscope with your smartphone? If you have, you know how much hassle it is to consistently take good, sharp microscope pictures. So maybe, annoyed with how cumbersome it is and how much time it takes, you have already looked for a microscope phone adapter? I know I have, and the one I got from Amazon quickly ended up in my drawer and never saw the light of day again. The pictures were no better than with the handheld phone and it took forever to mount that thing.

Disappointed with my Amazon experience I gave up on finding a microscope phone adapter, thinking a proper microscope camera was the only way to go. Then I saw a comment by Skoped Micro on one of my Instagram posts. This microscope phone adapter looked different, and it even featured a dedicated app to take pictures.

This is how I met Cade Wilson, a practicing veterinary surgeon from Oklahoma, who developed this unique microscope phone adapter together with the outdoor company Phone Scope, originally modifying it from a phone adapter designed for a hunting spotting scope.

Fast forward 5 years and this microscope phone adapter kit consisting of a Custom Phone Case and Microscope Eyepiece Adapter is ready for purchase and anyone who wishes to do digital pathology can do it through their phone with ease, without having to disrupt their workflow or having to spend thousands of dollars for a slide scanner.

Listen to the full episode to learn more about how Skoped Micro brings digital pathology to everyone, including veterinary practices, universities, and all other microscope users.

So if you need to start doing digital pathology, telepathology, teleteaching, or just want to take beautiful pictures through your microscope for your Instagram or other social media feed, without breaking the bank, look no more!

Digital Pathology Place is a proud affiliate of Skoped Micro and you can purchase the digital pathology kit for your phone (consisting of Custom Phone Case and Microscope Eyepiece Adapter) through our affiliate link:

Thank you!

This episode’s resources:

Skoped Micro website with all the necessary resources and YouTube videos (affiliate link)
Dr. Cade Wilson’s Veterinary Hospital in Ardmore, OK

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

29: An easy AI tool for pathology image analysis. How Aiforia empowers pathologists and scientists with supervised deep learning w/ Tuomas Ropponen, Aiforia

5 oktober 2021 | 40 min

How many times did you get annoyed when using non-intuitive digital pathology software? Have you already given up on digital pathology and image analysis or are you still looking for something powerful but easy to use?

Today’s guest, Tuomas Ropponen, the chief technology officer at Aiforia, is talking about the creation of a pathology image analysis platform whose core principles are “easy to use” and “accessible” - Aiforia.

Aiforia stands for artificial intelligence (AI) for image analysis (IA) and it combines cloud-based access with supervised deep learning for pathology image analysis. This is where pathologists and computer scientists collaborate closely to create tools that empower pathologists and give them access to the state-of-the-art image analysis methods.

Aiforia began as a teaching and telepathology platform for sharing whole slide images. But as soon as deep learning passed the reality check and started outperforming classical computer vision methods, Aiforia’s team knew that they had to incorporate this method into their platform. It would change the way pathology was done.

The decision about using supervised deep learning as the method of choice was based on the desire to supervise the teaching of the AI in a similar way as we supervise the teaching of students. Only by supervising and curating the inputs can we be sure that we get quality output. Teaching AI in a supervised manner happens through annotations, and annotations are a natural way that pathologists communicate.

Pathologists have always marked areas of interest on the glass and later digital slides. It has always been the way to show others what is important on the tissue. Adapting annotations for supervised deep learning as a way of showing AI what is important was a natural progression of how pathologists work.

Another core value at Aiforia is the close collaboration between pathologists and computer scientists. Those two groups currently work very closely together but fostering this open relationship and honest communication required a few iterations and a deeper understanding of each other’s ways of working.

For computer scientists, it was surprising that the pathology scoring and grading system often could not be directly reproduced by image analysis algorithms. For pathologists it was surprising that the algorithm results did not match their visual estimates from glass slides. The two groups had to sit together and start dissecting the pathology problems into smaller components as well as translating them into quantifiable tasks.

Suddenly it became clear to everyone that the Ki67 quantification in the tumor consists of first detecting the tumor epithelium and later identifying and counting the Ki67 positive and Ki67 negative cells within the epithelium.

When pathologists’ fatty liver scores of 70 or 80% were nowhere close to the absolute pixel area of fatty vacuoles in the liver tissue of max 20% it became evident that pathologists were subconsciously normalizing their scores and spreading them on a 0-100% scale. Coming together and analyzing the discrepancies as a team revealed that pathologists’ scores or estimates are often an imprecise and inconsistent benchmark to measure against. Everyone went back to the drawing board (or drawing tablet) and provided a more objective ground truth – annotations.

This close collaboration of pathologists and computer scientists as well as involvement of user experience designers helps dr

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

28: QuPath - open source quantitative pathology not only for pathologists w/ Pete Bankhead, University of Edinburgh

24 september 2021 | 56 min

With more than 170K total downloads and over 700 citations in scientific literature, QuPath is arguably the most popular open-source software for quantitative pathology and bioimage analysis. Today’s podcast guest, Pete Bankhead, the author of QuPath, is taking us behind the scenes of his software creation.

Even though Pete is now a senior lecturer in digital pathology at the University of Edinburgh, his digital pathology career actually started by accident. With an undergraduate degree in theology and a master’s in computer science, he started working on bioimage analysis during his PhD in biomedical sciences. He began using open-source software for image analysis, which was an excellent and very efficient way to work with static bioimages. So, during his post doc work he tried to apply open-source software to pathology whole slide images (WSI), unfortunately without success…The pathology WSI were just too big - it was not even possible to efficiently open them with any openly available software.

So he started his own software development – first by creating his own plugins for already available open-source programs, such as ImageJ. It sort of worked but not really… There was no way to coordinate the development and bring all his plugins together, so he started developing his own pathology WSI viewer.

That worked, and in the process, he realized that building software tools himself gave him a lot more freedom to solve problems in a way tailored to the specific challenges of digital pathology. He dove deeper into the project and created what we now know as QuPath – the open-source software for digital pathology image analysis.

During its development, the software evolved from a Ki67 quantification tool to a machine learning-powered, versatile image analysis software.

Listen to the full episode to learn

Who and what influenced Pete,
why is QuPath open-source,
why Pete fought for QuPath to stay open-source,
and what are the most important features of QuPath.

This episode’s resources:

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

27: Immuno-oncology 101 w/ Elfirede Nößner, HelmholzZentrum, Visiopharm advisor

6 september 2021 | 35 min

This episode is brought to you by Visiopharm

Cancer immunotherapy, aka immuno-oncology, is tapping into the power of our own immune system to fight cancer. There are multiple processes and immune cell populations involved in tumor immunology and digital pathology and whole slide imaging has allowed scientists to leverage the power of tissue image analysis to detect and quantify them.

Today’s podcast guest, Prof. Elfriede Noessner will walk us through the complexities of the immune system, explain how it is being influenced to cure cancer and what role tissue image analysis plays in the process.

In the course of her research she studied the following processes relevant for immuno-oncology together with the cells responsible for them:

· Killing: T-cells

· Removing the debris of the tumor: macrophages

· Antigen presentation: dendritic cells

· Antibody production: B-cells

· Immune response regulation: regulatory T cells and checkpoints: CTLA4 and PD1/PDL1

Killing is crucial for destroying the tumor, but without removing the debris of the killed cells the surrounding tissue will suffer.

Antigen presentation enables the immune system to see the enemy. If we do not have antigen presentation, the T-cells responsible for the killing process are blind.

Antibody production is an upcoming research area of immuno-oncology however the processes are not well understood yet.

Regulation of the communication – stopping the immune response, prevents overshooting. In the body’s fight against the tumor, this regulation is coming too early, it stops the T-cells before killing all the tumor cells. This is detrimental in tumor oncology. The stopping proteins are called checkpoints (e.g., CTLA4, PD1/PDL1) and to keep the T-cell attack going on, they need to be inhibited.

Seeing is believing, so visualizing the cells and checkpoints has a great convincing effect for the scientific community, but it is also crucial for evaluating the effectiveness of the immune system. It makes it possible to see if the immune cells are in the right location and in the right number. A great example of this proving that the numbers of T-cells in the tumor influence the patient prognosis more than the classical pathology grading is the Immunoscore® of colon cancer. Quantification with image analysis of the numbers and locations of T-cells in colon cancer patients changed the way colon cancer therapy was approached.

This was a breakthrough proving that T-cells can matter. However, they do not work all the time and the task of the scientists is to figure out how to activate them. We need to understand what regulates the T-cells – one aspect is the checkpoints the other part is the regulatory cells. If the regulatory cells are close to the T-killer cells, the killer cells are inhibited. This can be only evaluated in an image – the proximity of the different cell types matters, and image analysis is the only way to accurately determine this information.

The immune system is a complex entity, but in order to fight cancer, we need to understand and learn to influence it. Digital pathology and image analysis have become indispensabl

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

26: How to choose a digital slide scanner w/ Doug Stapleton, Hamamatsu

13 juni 2021 | 25 min

Hamamatsu digital pathology slide scanners

Are you looking for a whole slide scanner for your digital pathology projects? In this podcast episode Doug Stapleton, the Service Manager of the digital slide scanner division of Hamamatsu, is guiding us through this process.

He is listing 10 questions you need to ask before purchasing a whole slide scanner tailored to your digital pathology needs.

Question 1: What is your budget and throughput?

Question 2: What is your intended use now and in the future? Brightfield, immunofluorescence or both?

Question 3: What is the cross-organizational demand for scanning services?

Question 4: How much space do you need in the lab for your scanner?

Question 5: What size of pathology slides do you want to scan? Standard size or non-standard?

Question 6: What magnification will you be scanning at? 20x, 40x or other?

Question 7: Is it just the whole slide scanner or does it come with additional equipment?

Question 9: How easy is it to scan the slides? How many times do you need to click?

Question 10: How does the whole slide scanner integrate with other systems in your lab?

Bonus Question 11: Are any extras included in the package?

Is there a special functionality that you are interested in, such as:

- telepathology capabilities

- virtual slide conferences

- slide annotations

- or cloud storage options?

Hamamatsu offers all of these functions which makes them a potential one-stop-shop for all your digital pathology needs.

Answer the questions above and you will gain clarity on what you really need. Equipped with this information you can start “scanner shopping.”

Just remember, no matter which scanner you choose, always dry and clean your slides before scanning!

Listen to the full episode to gain more insights or read the blog post based on this podcast episode.

This episode’s resources:

Doug Stapleton LinkedIn profile

How to choose a whole slide scanner for digital pathology – the ultimate guide (blog post).

How to choose a whole slide scanner for digital pathology – downloadable questionnaire + PDF of the blog ar

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

25: Virtual H&E. How Instapath uses optical sectioning microscopy to accelerate pathology diagnosis w/ David Tulman, Instapath

16 maj 2021 | 35 min

https://digitalpathologyassociation.org/dpa-podcast-beyond-the-scope

Have you ever wondered if the pathology turn-around time could be faster and came to the conclusion that the only way to achieve that is to skip the tissue sectioning and staining? Now it is possible, with optical scanning microscopy by Instapath.

Today’s guest, David Tulman, is the chief clinical officer of Instapath, a small startup using optical scanning microscopy to image fresh tissue without fixing and staining it.

Working as a clinical trial manager exposed David to different areas of medicine, so he decided to dive deeper and get a Ph.D. However, pipetting for 12 hours a day for 5 years of the program to do basic research did not sound attractive…so he found a different program – a Ph.D. in bioinnovation. As a result of this program not only did he get his Ph.D. degree but also co-founded a biomedical startup company – Instapath, whose mission is to deliver pathology diagnoses to patients faster – while they are still on the operating table.

To achieve that, Instapath uses optical scanning microscopy. This cutting-edge technology can scan a piece of fresh, un-sliced tissue and virtually generate an image resembling a 5 um thick H&E stained section. This can be achieved by staining the tissue with fluorescent dies, one of them being eosin itself, which happens to be fluorescent. The dies are water-based and enable the generation of a high-resolution pseudo H&E image.

Instapath focuses on the speed of the pathology evaluation. For an 18-gauge biopsy the time from tissue removal from the body, through fluorescent staining, image processing, and upload to the image viewer is between two and three minutes. This is amazing compared to the traditional process that takes several days, or even frozen sections that should take around 20 minutes.

Current applications of Instapath’s technology and system include:

- sample screening for biobanking,

- alternative to fluorescent and confocal microscopy,

And in the near future, following the results of ongoing validation studies the company thinks there is a good chance that

- optical scanning microscopy could replace frozen section evaluation.

To learn more about Instapath visit: https://www.instapathbio.com/

Ps. David was a great guest of this episode but he is also a podcast host himself. Together with Giovanni Lujan, they co-host the “Beyond the Scope” podcast by Digital Pathology Association.

This episode’s resources:

Publications about optical scanning microscopy co-authored by the Instapath team:

Beyond the Scope podcast

Digital pathology crash course:

https://www.subscribepage.com/digital_pathology_crash_

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

24: What to consider when choosing an image analysis solution for phenotyping? (part 3) w/ Regan Baird, Visiopharm

11 maj 2021 | 14 min

Multiplexing mini-series Part 1: Introduction to multiplex for tissue image analysis (part 1) w/ Regan Baird, Visiopharm
Multiplexing mini-series Part 2: How to make sense of multiplex data with phenotyping? (part 2) w/ Regan Baird

This episode is brought to you by Visiopharm.

In this third and last episode of the multiplex mini-series with Regan Baird from Visiopharm we look at the considerations when choosing an image analysis software for phenotyping.

The two main points to consider when choosing phenotyping image analysis software are segmentation assistance and data visualization.

Segmentation assistance:

Before different markers are attributed to different cells in the tissue and cell phenotypes are determined, cell boundaries need to be delineated. The automatic delineation of these boundaries by image analysis software is called cell segmentation.

Cells in tissue slides can have different shapes and sizes, which depend on the plane of sectioning, heterogeneity of the investigated tissue, and the disease stage. This makes the task of segmentation challenging. Unlike in single-cell confocal microscopy images, where the cell borders are very well-demarcated, in tissue they often need to be estimated. A separate segmentation (e.g., membrane) marker can help significantly, but a perfect cell segmentation is not attainable.

To best estimate the cell boundaries, rule-based classical computer vision approaches or artificial intelligence (AI) – powered approaches can be used. In rule-based approaches, we are working with well-defined features on which the segmentation is based, but we need to make concessions. The AI-powered models are only as good as the examples we train the models on. To combine the advantages of both, Visiopharm offers an AI-based nuclear segmentation as the starting point and a rule-based and marker-based second step to obtain the most reliable cell segmentation for phenotyping.

Data visualization:

The adequate visualization and handling of the obtained data depend on the software used. To understand and interpret the multidimensional multiplex and phenotyping data we need to interpret graphs, plots, two-dimensional reduction plots, and other data visualizations for all the images in multiplex studies. In order to evaluate how well the phenotyping has performed and to export meaningful results, the correct visualization tools need to be used.

If you need assistance or have questions about multiplexing and phenotyping visit the Visiopharm’s website and contact the Visiopharm team.

This episode’s resources:

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

23: How to make sense of multiplex data with phenotyping? (part 2) w/ Regan Baird, Visiopharm

4 maj 2021 | 11 min

22: OracleBio's path to GCP compliant image analysis clinical trail support w/ Lorcan Sherry, OracleBio

2 maj 2021 | 47 min

Founded in 2011 by this episode’s guest, Lorcan Sherry, along with co-founder John Waller, OracleBio entered the digital pathology market with a unique value proposition – to be a contract research organization for tissue image analysis and help other organizations in their biomarker discovery work.

Fast forward 10 years and they evolved from a small service provider into a Good Clinical Practice (GCP) compliant organization supporting clinical trials, but still within the same paradigm of providing tissue image analysis services.

Originally using one software package (Definiens), they diversified into others such as HALO and Visiopharm to be able to utilize the best tool for the job as well as match what their clients might be using for their internal image analysis projects.

The transition to supporting clinical trials was a bit bumpy as Definiens abruptly discontinued the software license that OracleBio’s business was based on, but the organization quickly pivoted and secured a diverse image analysis toolbox which helped them stay in business. Currently, as image analysis methods are advancing and deep learning plays an important role in solving computer vision problems applied to pathology, OracleBio keeps expanding the toolbox incorporating not only ready-to-use software packages but also programming capabilities. This variety of tools allows them to address a wide range of projects in the most efficient way.

For a CRO specializing in tissue image analysis, it is critically important to provide adequate quality control of the image analysis results. This process has been incorporated into the operations from the very beginning. Each project starts with the evaluation of the image quality – are they good enough for image analysis? Is there enough tissue? What about the tissue processing artifacts and the quality of staining? Only images that passed the QC criteria are used for algorithm development.

In the next step, pathologists annotate the regions relevant for analysis (e.g., the tumor mass vs. the non-neoplastic tissue present on the slide) and later they provide region and cell annotations as ground truth for comparison with algorithm markups and correlation calculations.

Apart from the annotations, pathologists provide educational sessions for the image analysis scientists to increase their knowledge about the problems which are being addressed with image analysis with the various projects.

Although OracleBio is supporting projects along the whole drug development pipeline, their recent focus has been on supporting immune-oncology clinical trials, which lead the company on the path to GCP compliance. This was a big effort for the company and went far beyond image analysis quality control and software validation. This change affected the way work is done across the entire company and positioned OracleBio to bring in the image analysis capabilities to support clinical trials. While histologic techniques evolved from simple brightfield chromogenic single marker IHC stains to immunofluorescence-based multiplex, which are difficult to evaluate visually, the image analysis tools for this more complex imaging data lagged in terms of regulatory compliance. OracleBio’s decision to commit to GCP compliance definitely closed this gap.

Even though the company’s focus shifted to the clinical part of drug development, OracleBio continues to serve their smaller biotech clients throughout

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

21: Introduction to multiplex for tissue image analysis (part 1) w/ Regan Baird, Visiopharm

26 april 2021 | 10 min

Multiplexing mini-series Part 2: How to make sense of multiplex data with phenotyping? (part 2) w/ Regan Baird
Visiopharm
Top 20 Pathology podcasts you must follow in 2021

This episode is brought to you by Visiopharm.

After experimenting with multidimensional, multimarker, and multicolor single-cell imaging modalities during his postdoc at Beth Israel Deaconess Medical Center in Boston, looking at 2D images of tissue stained just with hematoxylin and eosin (H&E) seemed to him a bit simplistic…and then he was tasked with doing tissue image analysis (IA). When relying just on H&E, IA can be a very challenging task. So, to both simplify it and extract more information from the tissue, multiplex staining can be implemented.

In this three-part episode miniseries Regan Baird, Ph.D., scientific sales manager at Visiopharm introduces us to the concepts of multiplexing and cell phenotyping as well as to image analysis approaches relevant for multiplex data analysis.

Multiplexing in the context of life sciences is referred to as taking multiple measurements at the same time on the same specimen. With tissue slides the easiest method of multiplexing is immunohistochemistry (IHC) based virtual multiplexing where consecutive sections of tissue are stained with a single IHC marker and later each slide is imaged and co-registered to simulate the presence of several IHC markers in the tissue of interest.

More complicated, but more precise methods allowing for visualizing cellular colocalization of biomarkers include multicolor bright field IHC (visualizing up to five biomarkers per tissue but colocalizing reliably a maximum of only two biomarkers per cell), immunofluorescence (IF) potentially with spectral unmixing, to increase the number of biomarkers per tissue section as well as per cell to nine, and imaging mass cytometry where instead of chromogens or fluorophores heavy metals are used, which increases the number of biomarkers up to 60 in a single section of tissue.

All these multiplex modalities have their advantages and disadvantages, and the choice of the appropriate method should be guided by the design of the experiment as well as scientific and/ or diagnostic questions we want to address.

For example, currently a widely used application of IF multiplexing is phenotyping cells in the tissue. This not only allows for the characterization of single cells but also lets us interrogate and investigate spatial relationships between different cell populations giving us information about the interactome of different cells and the environment in which they live.

To learn more about phenotyping join us for the next episode of the Multiplexing Miniseries next week.

This episode’s resources:

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

20: Accelerating custom design of AI image analysis algorithms for drug development using transfer learning w/ Sylvain Berlemont, Keen Eye

4 april 2021 | 31 min

19: A new generation of whole slide scanners: faster, smarter, and more flexible w/ Don Van Dyke, Bionovation

14 mars 2021 | 26 min

18: Reimbursement for digital pathology in the clinic – how does that work? w/ Esther Abels, Visiopharm

8 mars 2021 | 31 min

Medical tests and procedures can get reimbursed. The basis of the reimbursement are the Current Procedural Terminology (CPT) codes developed by the American Medical Association (AMA).

But how can such a code be obtained for digital pathology which is so much more complex than a group of tests or procedures that could be reimbursed on a fee-for-service basis?

According to Esther Abels, Visiopharm’s Chief Clinical and Regulatory Officer, to align the digital pathology reimbursement with its value the fee-for-service paradigm needs to shift to a value-based reimbursement strategy.

To determine the real value of digital pathology for patient care we need to

- Articulate the services provided and define their added value and uniqueness in patient care (e.g. risk assessment, improvements in responses to therapy, delay in disease progression),

- Gather data relevant to support the claimed added value (e.g. cost-effectiveness data),

- Ensure that the reimbursed fee is based on a combination of technology use and physician involvement,

- And identify the key values relevant for the decision-making stakeholders.

Limited work has been done in this area so far, but if we look into the existing care decision-making and treatment patterns and analyze the claims for existing codes in the payers’ databases, we will be able to identify key datasets where digital pathology could make a difference and use this information to start applying for new CPT codes more aligned with digital pathology value.

To analyze what steps would need to be taken to prove to the payers that a digital pathology test deserves reimbursement, let us take a tangible example of the Visiopharm’s AI-assisted metastasis detection in Lymph nodes application.

This application has a technical, artificial intelligence-based screening component and a pathologist’s reviewing component. Currently in order to assess the presence or absence of cancer metastasis in lymph nodes several (even up to 60) lymph node sections need to be visually evaluated by a pathologist. Finding a metastasis in one of those slides is sufficient to make the diagnosis, but regardless all the other slides need to be reviewed as well. One of the benefits of the AI application would be to save the pathologist’s time, but reducing cost is not the only added value of such an application. The value proposition lies in adding value to patient care. In this case, using a computer algorithm would increase consistency and precision increasing the overall quality of the slide review. AI-aided slide review for metastasis would result in faster turn around not only for the cases where it was used but also for other cases, as the time for visual review could now be used for evaluation of other cases or spending more time on more complex cases again increasing the quality of patient care. Faster diagnosis means faster access to treatment, which often means shorter treatment times.

Every time we are able to point out and overcome limitations in the current standard of care with digital pathology applications we have both a legitimate reason to get reimbursed for its use and an incentive to fight for it if we want to make the patients’ lives better.

This episo

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

17: Why and how should pathologists keep up with AI? w/ David Harrison, University of St. Andrews

22 februari 2021 | 31 min

This episode is brought to you by Visiopharm

Artificial Intelligence is starting to cross from pathology research into pathology clinical practice. With several AI-based algorithms approved for clinical use in Europe and many more in the making, it is clear that rather sooner than later it will be an integral part of practicing pathology.

Does everyone practicing pathology have to keep up with this new trend? Those who wish not to and are close to retirement probably not, but everyone else probably yes. AI will become one of the pathologist's everyday tools and the use of this tool should be taught throughout the entire process of medical formation from medical student through to practicing pathologists through continuous professional education. AI is not scary, but it is a new technology we need to adopt, similar to how immunohistochemistry (IHC) was adopted.

IHC entered the pathology practice only in the 1980s and today most practicing pathologists are using this method as an integral part of their diagnostic workflow. It was brand new not so long ago and the pathologist community had to figure out this new method and leverage it to better serve patients. An analogous situation is happening now with AI.

Unlike some may fear, the primary benefit of AI is not necessarily to make the diagnosis and replace pathologists. The first thing that AI does is help pathologists manage workflow. It may sound unambitious but triaging cases that are safe/ normal, and allowing the pathologist to focus on cases that are more urgent or more high risk already benefits the profession tremendously and improves patient care.

Pathologists should keep up with AI both to leverage its power to help pathology as well as leverage the collective pathology knowledge in different aspects of the discipline for the development of reliable AI tools designed to help pathologists.

This episode's resources:
Prof. Dr. David Harrison researcher profile
iCAIRD
Visiopharm

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

16: Virtual Immunohistochemistry. How Owkin uses artificial intelligence to generate IHC stains without antibodies w/ Victor Dillard

31 januari 2021 | 34 min

15: Why and how is AI taking over the tissue image analysis field? w/ Jeppe Thagaard, Visiopharm

17 januari 2021 | 25 min

Machine learning is not a new technology, but it started to revolutionize pathology relatively recently. The ideal combination of untapped, abundant pathology data necessary to leverage machine learning and the relevance of pathology applications has drawn scientists to this field and caused an artificial intelligence (AI) explosion.

Within just two years from 2018 to 2020 AI-based tissue image analysis went from “cutting edge technology” to “mainstream”. The deep learning explosion started with the Camelyon challenge which served as a proof of concept for the technology. The algorithms performing best in breast cancer metastasis detection in lymph nodes were all deep learning-based. This success combined with greater accessibility of whole slide scanning and recently accessibility of open-source deep learning frameworks led us to where we are today.

In computer vision, the task of the computer is to analyze images in a way that mimics how humans see.

This can be achieved in three main ways:

· Through rule-based systems by understanding the visual problem and writing rules such as intensity threshold definition, to solve it.

· By machine learning, where we still determine the features of interest and manipulate the images to enhance the signal we are looking for, but the rules for detecting our features of interest are learned by the computer. We use approaches such as:

Random forest,
Bayesian classifier And other classical ML approaches

· and through deep learning, where both the features of interest and the rules to extract those features are learned from the data.

This characteristic is at the core of AI power in tissue image analysis. Deep learning enables us to solve problems we could not solve before.
It was not possible to solve many of the pathology tasks with rule-based systems because it was not possible to define rules complex enough to achieve a good output. Now that there is no need for rules this barrier has been removed, and we can just give examples of what we are looking for instead.

Now instead of writing code, our task is to collect and curate data and generate examples of the structures we are looking for. Deep learning delivers image analysis to a much larger user base and empowers users who were not previously trained in image analysis to take advantage of this technology. This is a major breakthrough in this field. Shifting the main task in designing image analysis from writing code to curating data contributed to the greater involvement of pathologists who are uniquely trained in interpreting tissue and crucial to the process of assuring the quality of the data. However, they are not the only ones who can do this, which broadens the user base of this technology even more.

Even though AI is so powerful and accessible, there is still tremendous value in the classical image analysis approaches and even more so in combing the classical rule-based and machine learning approaches with deep learning. Visiopharm’s platform enables this combined approach by having an ecosystem of classical and AI-based approaches that can play together to best solve the problem. In this way, the problem picks the method and not the other way around, which is how it should be.

In the long-term, AI will help us get more insights into the pathobiology of diseases by helping in the interpr

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

14: HistoQC, an open-source way to control the quality of pathology images

4 januari 2021 | 68 min

This episode's guest, Andrew Janowczyk, is a computer scientist who has been active in the field of digital pathology since 2008. Before turning to the field of digital pathology he worked across the globe and across industries.

He was a salmon fisherman in Alaska.
In Austria at the United Nations (UN) International Atomic Energy (IAE) Agency, he significantly contributed to the work that won the UN IAEA a Nobel Peace Prize.
He taught English in China.
He helped build an oil facility in the Nigerian jungle and lived in Nigeria for a while.
Then he lived in Germany...

A close family member diagnosed with cancer made him aware of the field of pathology and he decided to switch gears and put his energy and brainpower into advancing this discipline.

He moved to Mumbai, India to get his Ph.D. and started his digital pathology research. Currently, he is working at the Case Western Reserve University (OH, USA) and Lausanne University (Switzerland).

Fast forward to 2018, after 10 years in the field and after overcoming many challenges, he encountered another one: the suboptimal quality of the whole slides from the TCGA data set. To solve this he writes software that excludes all the non-usable regions of the slides and makes it open-source.

Why? Why not commercialize such a useful tool?

Andrew's answer: "I wanted to release it open source just to fundamentally change the world. I wanted to change the way that we enacted digital pathology as a science, and one of the problems with digital pathology science versus other sciences is that we don't take measurements. And as soon as we start taking measurements, we have the ability to do better."

In addition to his main work, Andrew also runs a blog with resources for computer scientists working in the field of digital pathology.

Other resources from this episode include:

Publication: HistoQC: An Open-Source Quality Control Tool for Digital Pathology Slides
Publication: Assessment of computerized quantitative quality control tool for kidney whole slide image biopsies
HistoQC download page
An article on Andrews blog about how to download TCGA digital pathology images

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

13: How Aira Matrix supports digital pathology with deep learning on demand w/ Chaith Kondragunta

14 december 2020 | 37 min

Today’s guest, Chaith Kondragunta, started working on neural network applications as an engineer back in the days when the computing power to fully utilize them was not available yet. This research field had to wait for the technology to catch up with the theoretical concepts. When this was achieved, Chaith harnessed deep learning for data analytics in the financial sector, but always knew, that to make a real difference it should be implemented in health care and medical sciences. This opportunity came in 2018 when he became the CEO of Aira Matrix – an image analysis company applying deep learning to pathology images.

Aira Matrix is based in Mumbai, India, and was definitely a pioneer in the tissue image analysis space in that region. They started when digitization in pathology was still far off in India and were serving mostly international clients. Currently more and more organizations in India are investing in digital pathology infrastructure, and Aira Matrix is standing strong in the local market as well.

The company started with image analysis software as a product, but to better address the needs of the medical and scientific community, gradually added services for building customized solutions to their portfolio.

Starting in the non-clinical toxicologic pathology area with solutions aiming to streamline the tox path study such as:

the team expanded their services into the clinical area focusing on prostate cancer.

Currently the standard grading system for this disease relies on the Gleason score – a system grading the difference in appearance of the prostate glands when compared to normal. This is done visually on a two-dimensional glass slide or a whole slide image. Thanks to deep learning pathologists can expand the diagnostic process by multiple parameters and modalities including volumetric prostate gland construction.

Aira Matrix was founded to solve complex toxicopathologic problems and is wired to think in terms of complex problems. In addition to that, with more than 50% of Aira’s employees having an advanced degree, the culture of research and innovation is embedded in the company. To stay on top of the game the team regularly takes part in different computer vision challenges.

To learn more about Aira Matrix visit: https://www.airamatrix.com/

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

12: Why and how should digital pathology be implemented into clinical practice? w/ Ralf Huss

2 december 2020 | 30 min

Implementing digital pathology into clinical practice is a big endeavor and a decision not taken lightly by pathology laboratories. Today’s guest, Dr. Ralf Huss, the chairman of Visiopharm’s advisory board explains:

· what the biggest benefits of going digital are

· how to start

· and why pathologists will be forced to accept the digital transformation.

Currently, the two greatest benefits of digital pathology which can be taken advantage of by every pathology practice are

· telepathology, enabling access to remote experts,

· and the ability to deal with complex biomarkers which can be tackled by image analysis and supported by access to experts and reference centers.

New biomarkers are being detected by very complex assays and digital pathology, especially its image analysis component, gives pathologists the ability to standardize the reading and reporting of such assays, which directly benefits the patients. This reduces the inter-and intra-pathologist variability and translates into consistent treatment decisions and quantitative data. The biomarker assessment is especially complicated in the field of immune-oncology and in this field image analysis is often the go-to evaluation method.

Going digital in a pathology lab can be a complex and daunting process. When starting the digital pathology journey, there are no “low hanging fruits” and the decision where to start depends on the needs and the availability of tools in each lab. The journey however should always start with a detailed plan and clear definition of goals and supporting action items.

Regarding digital pathology hardware and software, the market is saturated with great standalone products, but the key to helping labs go digital is to provide tools that are interoperable and can be immediately plugged into a functioning pathology workflow. All hospitals and pathology laboratories already use a lab information management system (LIMS) and have a functioning IT infrastructure as well as other tools that are there to stay. The new tools need to have an open interface and be interoperable with the old ones. Only this approach will grant the vendors success.

Even though the tools for digitalization of pathology have been available already for over two decades, only few institutions went fully digital and the lack of interoperability of the new and old pathology systems plays a major role in slowing down the digitalization process.

For most institutions going “fully digital”, defined as the entire workflow having accessible digital information attached to its every step, will not be immediately possible. The transition will happen slowly, as an evolution rather than a revolution and the interoperability of digital pathology systems with the rest of laboratory equipment and infrastructure will play an important role in deciding whether to go digital soon.

For now, some labs can decide to stay analog and still thrive, however, in the long run, the advances in medicine themselves will force pathologists to go digital. As the disease biomarkers get more and more complex, pathologists will require more and more help from image analysis and advanced analytic tools. However, to be truly helpful, these tools need to be user-friendly, robust, and standardized.

Visiopharm is striving to provide such tools and with its image analysis solutions, the c

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

11: DIY AI-based image analysis for pathology. How DeePathology incorporated respect for pathologists' time into their software w/ Chen Sagiv

20 september 2020 | 32 min

I met Chen Sagiv in person in 2019 at the European Congress of Toxicologic Pathology in Cologne, Germany after previously interacting for several months on social media. We stayed in touch ever since and started working on several projects together. Because of her expertise and the great relationship we have developed, she is now my go-to person in the computer vision field.

Chen is a mathematician and a computer scientist specialized in computer vision. She is the founder of several tech companies and one of them - DeePathology- has the goal of democratizing pathology. DeePathology's mission is to bring artificial intelligence to pathologists and to make it as easy and as user friendly as possible. DeePathology's software - The Studio - is designed not only to be easy to use for pathologists and life scientists but also to shorten the time required to perform annotations.

Annotating structures for training deep learning models is a time consuming and tedious task. By incorporating the principles of active learning into the software the time necessary to generate annotations is significantly reduced. After providing the model with some examples of the structures of interest it starts learning and actively asking the user to review the non-annotated structures recognized by the algorithm. This respect for pathologists' time is something rarely incorporated into digital pathology software design.

Digital Pathology Place and DeePathology are hosting a webinar series called "When a Pathologist meets a Mathematician" where we bridge the pathology and computer science concepts. To join our next webinar
"The Good, the Bad and the Biased - How can pathologists assess the correctness of AI?"
Register here

To learn more about artificial intelligence register for Chen's free
"AI for Pathologists" course here
In this course, Chen explains the AI principles to pathologists and life scientists who are interested in the subject and want to understand and implement this discipline into their own work.

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

10: Remote toxicologic pathology. How Deciphex is accelerating the non-clinical drug development phase w/ Donal O'Shea.

7 september 2020 | 48 min

The guest of this episode is Donal O'Shea, the CEO, and founder of Deciphex. He has been active in the area of digital pathology essentially since its beginning. He worked in academia and founded several successful digital pathology start-ups before his current one.

Deciphex, in contrast to most digital pathology companies, is focused on non-clinical pathology, and its mission is to facilitate the complete digitization of this space and to contribute to the faster turnaround time of drug development. The means to achieve these goals are two software products: Patholytix preclinical and Patholytics AI.

One of the reasons that the world of toxicologic pathology was lagging behind the world of diagnostic pathology in the digitization efforts was the lack of solutions tailored to this market. Deciphex decided to address all the particularities and nuances of the toxicopathologic workflow through close industry collaborations and by bringing the users to the table during the product development process. This resulted in software that delivers nearly an analog user experience away from the microscope.

Non-clinical pathology may seem like a very niche market, but it is one with very high throughput, handling millions of glass slides every year. Accelerating the review of those slides can contribute to tremendous efficiency gains in the pharmaceutical industry.

Deciphex is tackling this challenge by enabling organizations to do digital pathology peer reviews of toxicopathologic studies. Pathology peer review is typically connected either with the travel of the peer review pathologists or with the shipment of the slides to them, both of which are time-consuming, costly, could result in glass slide damage and disrupt the normal pathology workflow. All this could be eliminated with a digital workflow, which is extremely desired especially during the COVID-19 pandemic. Digital peer review (and in the long term also digital primary review) can be enabled by the Patholytix preclinical software

Another area where Deciphex is focused on helping the pharma industry gain efficiency is artificial intelligence-based generalized abnormality detection in the whole slide images (WSI). This image analysis-based decision support system would flag abnormalities in the WSIs requiring a pathologist review without indicating a diagnosis. This would be of especially great benefit to toxicologic pathology in comparison to diagnostic pathology because most of the slides in a toxicopathologic study are normal. If the review of normal slides could be accelerated by reducing the number of normal slides requiring pathologists' evaluation and allowing them to focus mostly on the abnormal ones the time necessary for study review would decrease tremendously. These improvements would be made possible by the Patholytics AI software as an addition to Patholytix preclinical.

To remain agile and responsive to the newest computer vision and digital pathology trends Deciphex products ma

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

9: Digital pathology in a suitcase. How Grundium's portable whole slide scanning microscope expands the reach of telepathology w/ Mika Kuisma

3 juli 2020 | 27 min

Often those pathologists and scientists who are thinking of starting their journey with digital pathology are intimidated by the workflow changes and investment they will have to make in order to get started. The cost of the equipment and the challenges related to workflow re-design are often a significant barrier for adoption.

Good news, there is an alternative! My guest, Mika Kuisma, the CEO of Grundium, together with his colleagues have been working on a solution since 2015.

Mika and his colleagues worked together in the mobile phone industry for many years and mastered the portable communication device technology. When mobile phones became a commodity the next step was to find a meaningful application that could positively impact peoples' health and wellbeing. The technology and lessons learned from the mobile phone space and the problems encountered in pathology turned out to be a great match and this is how their portable digital whole slide imaging (WSI) microscope was created.

The device is only 18x18x19 cm (7x7x7.4″) in size and weighs just 3,5 kg (7.7 lb) and is in the lower price range in this WSI product category. This totally portable scanning microscope takes just a few minutes to set up, scans a 1.5x1.5 cm tissue piece in about 2 minutes, and has a built-in artificial intelligence (AI)-based automated specimen recognition feature. This small, smart device was developed for on-demand telepathology to enable pathologists and other medical professionals to provide an accurate diagnosis for everybody from anywhere. The main applications of personal digital microscopy, second opinion, and telemedicine complement the current WSI scanner market offer. It is non-disruptive to the existing workflow and through an open API can be connected to different software applications already in use in the laboratory.

Grundium's goal is to make the scanner even more intelligent by collaborating with third-party companies on AI-based image analysis algorithms as well as further utilizing the internal AI to make the device as user friendly and intuitive as possible.

Listen to how Mika describes the company's and the product's evolution and stay tuned for a more detailed product review with a video demonstration coming soon at the Digital Pathology Place.

Become a Digital Pathology Trailblazer get the "Digital Pathology 101" FREE E-book and join us!

8: What is validation and how to validate an AI image analysis solution with Tom Westerling-Bui from Aiforia

4 juni 2020 | 55 min

The tools to develop AI models for biomedical image analysis have recently become accessible also for non-computer scientists. With the accessibility to AI tools, the question arises whether the things we build are good enough?

How do we check the model?

How do we validate it and be sure that when deployed according to the intended use it will perform adequately and help us make the right decisions based on the correct premises?

In this episode, Thomas Westerling-Bui from Aiforia explains the validation principles that should be applied to AI image analysis solutions.

The AI image analysis model validation is like any other assay validation. It starts with finding out the boundaries of the assay's usability. As for any assay, also in the case of an AI model its precision and recall are the most important parameters we want to check. We need to perform a conceptual validation and find out if the platform used does what we want it to do and an analytical validation to precisely quantify the accuracy of the method.

Validation is different from improving the AI model on a given data set and always needs to be performed on an independent data set. Unfortunately, there seems to be confusion about that in the scientific community which weakens many of the biomedical publications describing the development and use of AI models.

Another important concept - the intended use, is crucial not only for the use of the assay but also for its validation. The validation of a screening tool will be performed differently than the validation of a diagnostic tool.

As powerful as they are, the AI-based tools are just tools and will not do the things they are not designed (trained) to do so the validation should be tailored to the things they ARE trained to do.

As supervised AI methods rely on human-generated ground truth both for training and for validation the decision of how many validation regions to include depends heavily on the human capacity to provide adequate ground truth - in the case of image analysis it often includes annotations. If the users are pressed to generate a large number of annotations, precision may suffer so a middle ground needs to be found to provide an adequate number and maintain precision.

Another important aspect of generating ground truth is interobserver variability. It needs to be quantified and accounted for during the validation, which is why comparing model outputs against ground truth generated by just one individual is of limited value.

In a nutshell, the subject is complex, and to understand these and other nuances of AI model validation the following resources may be of use:

Online courses:

Coursera:
Other:
- Elements of AI

Books:

Practical statistics for data scientists