Computer vision to deeply phenotype human diseases and aging across physiological, tissue and molecular scales

About this Class

Speaker: James Zou, Ph.D., Assistant Professor, Biomedical Data Science, Computer Science, and Electrical Engineering, Stanford University Register Dr. Zou will present new computer vision algorithms to capture complex morphologies and phenotypes that are important for human diseases and aging. He will illustrate this with examples from different physical scales: 1) video AI to assess cardiac function (Ouyang et al Nature 2020), 2) generating spatial transcriptomics and protein profiles from histology images (He et al Nature BME 2020), and 3) learning morphodynamics of immune cells. This talk will also give an overview of general design principles and tools developed to enable these technologies. Biography: - Chan-Zuckerberg Investigator and the Faculty Director of Stanford AI for Health. - Dr. Zou develops novel machine learning algorithms that have strong statistical guarantees and that are motivated by human health challenges. - Methods used are widely used by tech, biotech, and pharma companies. - Works on questions important for the broader impacts of AI, e.g., interpretations, robustness, fairness, and data governance. - Received several best paper awards at top CS venues, an NSF CAREER Award, a Google Faculty Award, and a Tencent AI award. Individuals with disabilities who need Sign Language Interpreters and/or reasonable accommodation to participate in this event should contact Prisca N. Fall, fallpn@mail.nih.gov, 301-402-4582, and/or the Federal Relay (1-800-877-8339).