IBIIS & AIMI Seminar: Computer Vision to Phenotype Human Diseases Across Physiological and Molecular Scales

Jan 20, 2021 (Wed) | 12:00 PM -1:00 PM
318 Campus Drive : Stanford, CA

Zoom Link Information: https://stanford.zoom.us/j/92228631667?pwd=MjVsakhoUU1wL2psczRGaW9SOWhrUT09
Abstract
I will present new computer vision algorithms to learn complex morphologies and phenotypes that are important for human diseases. I will illustrate this approach with examples that capture physical scales from macro to micro: 1) video-based AI to assess heart function (Ouyang et al Nature 2020), 2) generating spatial transcriptomics from histology images (He et al Nature BME 2020), 3) and learning morphodynamics of immune cells. Throughout the talk I'll illustrate new design principles/tools for human-compatible and robust AI that we developed to enable these technologies (Ghorbani et al. NeurIPS 2020, Abid et al. Nature MI 2020).

Department:  Radiology

Contact: Ramzi Totah | 16507214161 | rtotah@stanford.edu

Presenter(s):