Visualizing Cancer Margins with Ersin Bayram from Perimeter Medical Imaging AI

Today, I am joined by Ersin Bayram, the director of AI and data science at Perimeter Medical Imaging AI, to talk about tissue imaging during cancer surgery. This technology provides real-time margin visualization to surgeons intraoperatively vs. waiting days later for the pathology report, which remains the gold standard for confirming margin status. The surgical oncologists’ goal is to achieve clean margins on excised tissue during the initial surgery and reduce the chance of the patient requiring a second surgery or leaving some cancerous tissue behind. The next generation of this device uses AI and big data to speed image interpretation.

Tuning in, you’ll hear about the role of machine learning in this technology, how they gather and annotate data in order to train the system, and the types of challenges encountered when working with OCT imagery. We discuss the role of model explainability, whether or not model accuracy is more critical, and how classic activation maps are used for improving the model. We also talk about regulatory processes as well as Ersin's approach to recruiting and onboarding before he gives his advice to other leaders of AI-powered startups. For all this and more, tune in today!

Key Points:

• An introduction to Ersin Bayram and his role at Perimeter Medical Imaging AI. 
• What Perimeter does and why this is important for cancer outcomes. 
• The role of machine learning in this technology. 
• How this technology segments out potential areas of concern on the OCT scans and displays this to the surgeon.  
• How Perimeter Medical Imaging AI gathers and annotates data in order to train the system.
• The types of challenges they encounter when working with OCT imagery. 
• The role of model explainability and whether or not model accuracy is more critical. 
• How classic activation maps are used for improving the model and not shown to the clinician.  
• How the regulatory process affects the way Ersin and his team develop machine learning models. 
• Approaches to recruiting and onboarding that have been most successful. 
• Ersin’s advice to other leaders of AI-powered startups. 
• How he foresees the impact of Perimeter three to five years from now.

Quotes:

“I can still work on oncology, making an impact on a really deadly disease, and also start focusing entirely on the AI side and the data science aspect. That was an easy decision.” — Ersin Bayram

“The surgeon might be able to look into the images and then they might be able to go back and take extra shaves or there might be also benefits not to carve out healthy tissue more than needed.” — Ersin Bayram

“If you find the talent that has the medical imaging background and they have the foundational skills, technical thinking, and they have basic Python skills, we can train them and we can ramp them up to become good AI scientists.” — Ersin Bayram

Links:

Ersin Bayram

Perimeter Medical Imaging AI

Disclaimer:
Perimeter B-Series OCT is not available for sale in the United States. CAUTION – Investigational device. Limited by U.S. law to investigational use.

Resources for Computer Vision Teams:

LinkedIn – Connect with Heather.

Computer Vision Insights Newsletter – A biweekly newsletter to help bring the latest machine learning and computer vision research to applications in people and planetary health.

Computer Vision Strategy Session – Not sure how to advance your computer vision project? Get unstuck with a clear set of next steps. Schedule a 1 hour strategy session now to advance your project.

Computer Vision Advisory Services – Monthly advisory services to help you strategically plan your CV/ML capabilities, reduce the trial-and-error of model development, and get to market faster.