Clinical AI at Scale: Adaptive Radiotherapy, Federated Learning, and Contrastive Foundation Model Training
Department of Biomedical Engineering
Location: Edwin A. Stevens, Room 222
Speaker: Yading Yuan, PhD, Herbert and Florence Associate Professor of Radiation Oncology (Physics), Data Science Institute, Columbia University Medical Center
Abstract
As a cornerstone of cancer treatment, radiation therapy is a data- and workflow-intensive specialty that relies on high-quality imaging, accurate target and organ-at-risk delineation, optimized treatment planning, and rigorous quality assurance to deliver safe, personalized treatment. These steps are time-sensitive and often require substantial manual effort, creating bottlenecks that can delay care and introduce variability across clinicians and institutions. AI is rapidly moving from retrospective proof-of-concept studies to prospective, workflow-integrated tools that can help streamline clinical practice and improve patient care. Critically, automation is a key enabler of adaptive radiotherapy by helping “plan-of-the-day” adaption achievable within clinical time constraints.
In this talk, I will discuss our approach to building clinical AI at scale for radiotherapy and medical imaging, spanning model development and evaluation in clinical constraints, privacy-preserving multi-institutional learning, and probabilistic contrastive representation learning strategies that support foundation model training. I will highlight practical clinical translation, with an emphasis on generalizability, safety, and scalable collaboration across sites.
Biography
Yading Yuan, PhD is the Herbert and Florence Associate Professor of Radiation Oncology (Physics) (in the Data Science Institute) at the Columbia University Medical Center. He received his PhD in Medical Physics from the University of Chicago and completed clinical residency training at the Harvard Medical Physics Residency Program. His research lies at the intersection of computer engineering, physics and medical imaging, with a focus on advancing clinical and scientific innovation in radiation therapy. His current work centers on medical image computing, trustworthy AI, personalized federated learning, and clinical AI agents in radiotherapy. He is board-certified by the American Board of Radiology in therapeutic medical physics.
At any time, photography or videography may be occurring on Stevens’ campus. Resulting footage may include the image or likeness of event attendees. Such footage is Stevens’ property and may be used for Stevens’ commercial and/or noncommercial purposes. By registering for and/or attending this event, you consent and waive any claim against Stevens related to such use in any media. See Stevens' Privacy Policy for more information.
