September
Tuesday, September 23, 2025
8:00-9:00am PT
Watch Recording Here
Lei Xing, PhD
Jacob Haimson & Sarah S Donaldson Professor
Stanford University
Title: Biomedicine in the Age of AI and Foundation Models
Abstract: AI and Foundation Models (FMs) are revolutionizing biomedical research and medicine, offering a critical path to breakthrough discoveries and substantially improved patient care. However, their full potential is hindered by significant challenges related to their training and fine-tuning. Current deep learning models often rely on a brute-force approach that ignores crucial prior system knowledge, leading to extensive data requirements and suboptimal performance. In this talk, I will elaborate on the important role of prior system knowledge in deep learning models and introduce strategies to integrate this information into the data-driven decision-making process. I will demonstrate the efficacy of this novel framework through applications in biomedical imaging and omics data analysis. Integrating prior knowledge substantially improves computational efficiency, enhances interpretability, and reduces the incidence of model hallucinations, accelerating scientific discoveries and advancing personalized medicine.
Dr. Lei Xing is the Jacob Haimson & Sarah S. Donaldson Professor and Director of Medical Physics Division of Departments of Radiation Oncology and Electrical Engineering (by courtesy) at Stanford University. He obtained his PhD from the Johns Hopkins University. His research is focused on AI in medicine, data science, medical imaging, and clinical decision-making. Dr. Xing is an author on more than 450 publications in high impact journals, an inventor/co-inventor on many issued and pending patents. He is a fellow of AAPM, ASTRO, and AIMBE. He is the recipient of the 2019 Google Faculty Research Award, and 2023 Edith Quimby Lifetime Achievement Award of AAPM, which denotes outstanding scientific achievements in medical physics, influence on the professional development of others, and organizational leadership.