"Toward Scalable and Generalizable AI for Medical Image Analysis: From Federated Learning to Probabilistic Representation Learning"
Yading Yuan, PhD, DABR
Herbert and Florence Associate Professor of Radiation Oncology (Physics) (in the Data Science Institute)
Vagelos College of Physicians and Surgeons
Columbia University Irving Medical Center
Medical imaging AI is moving toward models that can learn across institutions while adapting to diverse patient populations and imaging conditions. This seminar explores approaches to building scalable and robust AI, from personalized federated learning for collaborative model development without sharing patient data, to probabilistic representation learning that improves generalizability and reduces dependence on manual annotations.
This research seminar is hosted by the Center for Innovation in Imaging Biomarkers and Integrated Diagnostics (CIMBID) and the Data Science Institute (DSI).
EVENT DETAILS:
November 20, 2026
12:30 PM - 1:30 PM
Pizza and drinks will be served starting at noon!
Radiology Administration Offices
622 West 168th Street, PH1-317
Conference Room 303
New York, NY 10032
REGISTRATION:
Please register using your UNI. This is a hybrid event, open to all members of the Columbia University community. A Zoom link will be provided to all registrants.