MICCAI Industrial Talk: Translating AI to Clinical Practice
Wednesday 15th January 2025
Join us for the next exciting Industrial Talk:
Translating AI to Clinical Practice:
Addressing real-world challenges in data, annotation, model robustness, validation and deployment
Monday, January 27, 2025
10:30 - 11:30 am EST / 4:30 - 5:30 pm CET
Speaker: Dr. Alvin Chen, Senior Research Scientist and Group Lead, Philips
Abstract:
Despite significant advancements in AI and machine learning for healthcare, translating these technologies into clinically approved medical devices remains challenging. This talk examines key barriers to developing and deploying robust AI models for clinical use, including data limitations, annotator variability, and model design considerations. Using AI-based computer-aided detection of lung infectious diseases as a case study, we highlight strategies to address these obstacles, such as modeling annotator consistency, leveraging self-supervised and semi-supervised learning to reduce annotation burden, and augmenting with synthetic images to address data imbalance. We also discuss critical considerations in understanding the clinician-AI interface and designing effective clinical validation studies, and provide an overview of FDA pathways for AI/ML-enabled medical devices.
Speaker Bio:
Alvin Chen is a Senior Scientist and Group Lead at Philips, where he specializes in the development of AI-powered ultrasound imaging and diagnostic technologies to improve healthcare access and emergency response, particularly in point-of-care settings. His team focuses on developing and applying machine learning techniques and best practices to address challenges in medical data, annotation, and clinical validation of these technologies. Dr. Chen has co-authored over 30 peer-reviewed publications and more than 50 patents or patent filings. He earned his Ph.D. in Biomedical Engineering from Rutgers University.