Stanford Medical AI and Computer Vision Lab

The Medical AI and ComputeR Vision Lab (MARVL) at Stanford is led by Serena Yeung, Assistant Professor of Biomedical Data Science and, by courtesy, of Computer Science and of Electrical Engineering.

Our group's research develops artificial intelligence and machine learning algorithms to enable new capabilities in biomedicine and healthcare. We have a primary focus on computer vision, and developing algorithms to perform automated interpretation and understanding of human-oriented visual data across a range of domains and scales: from human activity and behavior understanding, to human anatomy, and human cell biology.

Our group is also affiliated with the Stanford AI Lab (SAIL), the Stanford Center for Artificial Intelligence in Medicine & Imaging (AIMI), and the Stanford Clinical Excellence Research Center (CERC).

Research Areas

human behavior

We develop algorithms to recognize and interpret human activities, pose, and behavior, for applications including AI-assisted hospitals and study of early childhood development.

human anatomy

We develop algorithms to perform automated interpretation of medical image data ranging from radiology to surgical video, for applications including diagnosis and AI-assisted surgery.

human cell biology

We develop algorithms to analyze cell microscopy images at scale, in order to obtain insights into the structure and function of subcellular components in healthy and diseased cells.

News & Updates

  • We have openings on a rolling basis for postdocs, rotation PhD students (already accepted to Stanford), and a limited number of MS or advanced undergraduate students. If you would like to be a postdoctoral fellow in the group, please send Serena an email including your interests and CV. If you are a Stanford PhD student interested in joining the group, please send Serena an email including your interests, CV, and transcript. If you are a current student in other degree programs at Stanford, please fill out this interest form (sign-in using your Stanford email address). For others not currently at Stanford, we apologize if we may not have the bandwidth to respond.


    Dec 2020: Joy and Jeff present a contributed talk on our work "Learning Hyperbolic Representations for Unsupervised 3D Segmentation" at the NeurIPS 2020 Differential Geometry meets Deep Learning Workshop.

    Nov 2020: Michael presents our work "Using Computer Vision to Automate Hand Detection and Tracking of Surgeon Movements in Videos of Open Surgery" at AMIA 2020.

    Aug 2020: We have received a Chan-Zuckerberg Initiative Neurodegeneration Challenge Network Collaborative Pairs Award (together with the Wah Chiu group).