12th CVPR Workshop on Medical Computer Vision

Full Keynote Series

Overview

Medical computer vision is reshaping the future of healthcare by uniting computer vision, machine learning, and clinical imaging into a shared scientific endeavor. Progress in this field is driven by cross-disciplinary collaboration, spanning algorithm design, imaging physics, robotics, and clinical translation, and is advancing our ability to understand, diagnose, and treat disease through intelligent visual reasoning. This workshop brings together leading experts from academia, healthcare, and industry whose research collectively spans foundation models, surgical vision, embodied AI, and data-centric learning. Through their perspectives, the event will promote open dialogue on key challenges in scalability, reliability, interpretability, and clinical integration. The broader impact of this workshop lies in shaping a unified research vision for trustworthy, human-centered, and globally accessible medical AI systems. By bridging technical innovation with clinical practice, it will catalyze new collaborations, establish shared benchmarks, and accelerate the translation of computer vision from research to real-world healthcare impact.

Keynote Schedule

Keynote session I

• 9:15–9:45 am Dimitris N. Metaxas

• 9:45–10:15 am Daguang Xu

• 10:15–10:45 am Sharon X. Huang

• 10:45–11:15 am Mathias Unberath

• 11:15–11:45 am Archana Venkataraman

Keynote session II

• 1:00-1:30 pm Maddie Traverse

• 1:30–2:00 pm Hoifung Poon

• 2:00–2:30 pm Jeremias Sulam

• 2:30–3:00 pm Kayhan Batmanghelich

• 3:00–3:30 pm Ehsan Adeli

• 3:30–4:00 pm Mert R. Sabuncu

• 4:00–4:30 pm René Vidal

Agenda Details

Opening Remarks

• 9:00-9:15 am

Keynote session I 

• 9:15-9:45 am Dimitris N. Metaxas

Explainability, Generation, Physics and Dynamics in ML for Biomedical  Applications

Dimitris N. Metaxas is a Board of Governors and Distinguished Professor in the Computer and Information Sciences Department at Rutgers University. He is directing the CBIM Center and the NSF University-Industry Collaboration Center CARTA, and is also a member of the RAD Collaboratory. Dr. Metaxas has been conducting research in the general area of spatiotemporal intelligence. The focus is the development of novel methods and algorithms upon which AI, machine learning, computer vision, medical image analysis, language and graphics/generative methods can advance synergistically in the presence of dynamic spatio-temporal multimodal data and domain knowledge. In biomedical image analysis he developed Machine Learning and deformable model-based methods for material modeling and shape estimation of internal organs from MRI, SPAMM and CT data, explainable diagnosis methods, cancer and cell, analytics. Dr. Metaxas has published over 800 research articles in these areas and has graduated over 80 PhD students, who occupy academic and industry positions. His research has been funded by NIH, NSF, AFOSR, ARO, DARPA, HSARPA, and the ONR. Dr. Metaxas work has received many best paper awards and he has 10 patents. He was awarded a Fulbright Fellowship in 1986, is a recipient of an NSF Research Initiation and Career awards, and an ONR YIP. He is a Fellow of the American Institute of Medical and Biological Engineers, a Fellow of IEEE and a Fellow of the MICCAI Society. He has been involved with the organization of all major conferences in computer vision and medical images analytics ( IEEE ICCV 2031, IEEE CVPR 2026, IEEE CVPR 2014, ICCV 2011, IPMI 2025, DDDAS 24&26, MICCAI 2008; PC ICCV 2007,  FIMH 2011 and SCA 2007). 

• 9:45-10:15 pm Daguang Xu

Driving AI Innovation in Healthcare through Open Data and Foundation Models​

Daguang Xu is a Senior Research Manager at NVIDIA, where he leads research in healthcare AI and medical imaging. His work focuses on deep learning, computer vision, federated learning, and AI infrastructure for clinical applications. He is a core contributor to the open-source MONAI and NVIDIA FLARE platforms. Daguang Xu received his Ph.D. in Electrical and Computer Engineering from Johns Hopkins University and has published extensively in medical AI and imaging analysis.  

• 10:15-10:45 am Sharon X. Huang

Advancing Diagnostic Robustness and Privacy-Preserving Model Training with Medical Image and Video Generation

Sharon Xiaolei Huang is the David Reese Professor and Department Head in the College of Information Sciences and Technology at Pennsylvania State University. Her research focuses on medical AI, computer vision, biomedical image analysis, and machine learning, with contributions to image and video generation, segmentation, and computer-assisted diagnosis. She has published more than 200 scholarly articles and serves in leadership and editorial roles for major AI and medical imaging conferences and journals.

• 10:45-11:15 am Mathias Unberath   

Digital Twins for Ambient and Embodied Surgical AI

Mathias Unberath is the John C. Malone Associate Professor of Computer Science at Johns Hopkins University. He leads the ARCADE Lab, where his research focuses on AI, computer vision, robotics, and mixed reality for computer-assisted medicine. His work develops human-centered technologies to support clinical decision-making and image-guided interventions. He has received multiple honors, including the NSF CAREER Award and NIH Trailblazer Award.

• 11:15-11:45 pm Archana Venkataraman 

Lightweight and Interpretable AI as a New Window into Brain Dysfunction

Archana Venkataraman is an Associate Professor in the Department of Electrical and Computer Engineering at Boston University, with joint appointments in Biomedical Engineering and Computer Science. Her research focuses on machine learning, artificial intelligence, medical imaging, and computational neuroscience, particularly for understanding brain disorders and mental health. She develops data-driven methods to study brain connectivity and multimodal biomedical data, with applications in neuroscience and precision medicine. Dr. Venkataraman has received several honors, including the NSF CAREER Award and multiple NIH-funded research awards.

Keynote session II

• 1:00-1:30 pm Maddie Traverse

MedGemma: an open vision-language model for diverse medical applications

Maddie Traverse is a Senior Software Engineer at Google Research, specializing in the intersection of deep learning, computer vision, and healthcare. Since 2023, Madeleine has focused on Google’s medical initiatives. She drove the machine learning development for Google's CT Foundation model and is a key contributor to MedGemma.Her broader work at Google includes designing graph neural networks for population health, advancing geospatial foundation models, and leading large-scale machine learning pipelines for personalized recommendation systems. Maddie has a long-standing focus on computer vision, having built deep learning classifiers for radiological evaluation and previously researched 3D GANs at UC Berkeley.

• 1:30-2:00 pm Hoifung Poon

Learning the Language of Patients: Multimodal Generative AI for Precision Health

Hoifung Poon is General Manager at Health Futures in Microsoft Research and an affiliated faculty at the University of Washington Medical School. He leads biomedical AI research and incubation, with the overarching goal of structuring medical data to optimize delivery and accelerate discovery for precision health.

• 2:00-2:30 pm Jeremias Sulam

Flexible methods for uncertainty quantification in medical imaging

Jeremias Sulam is the William R. Brody Scholar and Associate Professor in the Department of Biomedical Engineering and is also affiliated with the Mathematical Institute for Data Science and the Center for Imaging Science. He holds a secondary appointment in the Department of Applied Mathematics and Statistics and is a member of the Data Science and AI Institute. Jeremias’ research focuses on the foundations of machine learning and applications to biomedical imaging. He is interested in learning under parsimonious structures in data, robustness, and ethical implications of data-driven methods, as well as in the interpretability and auditing of the resulting models. His work is motivated by applications of diagnostic imaging in radiology, inverse problems, and biomarker discovery in neuroscience and digital pathology.

• 2:30-3:00 pm Kayhan Batmanghelich

Image-Text Foundational for Volumetric Image: Challenges and Opportunities 

Kayhan Batmanghelich is an Assistant Professor in the Department of Electrical and Computer Engineering at Boston University. His research focuses on medical image analysis and the broader application of artificial intelligence in healthcare. Previously, he was a faculty member in the Department of Biomedical Informatics at the University of Pittsburgh. He received his PhD from the University of Pennsylvania. He is a recipient of the NSF CAREER Award and a Google Academic Research Award.

• 3:00-3:30 pm Ehsan Adeli

From Bedside to Living Room: Reimagining Care Through Ambient Intelligence

Ehsan Adeli is an Assistant Professor of Psychiatry and Behavioral Sciences at Stanford University, with courtesy appointments in Computer Science and Biomedical Data Science. He directs the Stanford Translational AI (STAI) in Medicine and Mental Health Lab. His research lies at the intersection of artificial intelligence, computer vision, computational neuroscience, and digital health, with applications in mental health, aging, neurodegenerative disorders, and human behavior analysis. Dr. Adeli develops AI methods for multimodal biomedical data, including imaging, video, and sensor-based health monitoring.

• 3:30-4:00 pm Mert R. Sabuncu

Prevalence Adjustment as a Way to Handle Distribution Shift in Medical Vision

Mert R. Sabuncu received a PhD degree in Electrical Engineering from Princeton University, where his dissertation focused on entropy-based approaches to image registration. Mert then moved to the Massachusetts Institute of Technology for a post-doc with Polina Golland at the Computer Science and Artificial Intelligence Lab, where he worked on a range of biomedical image analysis problems, including the segmentation of brain MRI scans. After his post-doc at MIT, Mert spent a few years at the A.A Martinos Center for Biomedical Imaging (Massachusetts General Hospital and Harvard Medical School) as a junior faculty member, where he built a research program on algorithmic tools for integrating genetics and medical imaging. Today, Mert is a Professor in Electrical and Computer Engineering at Cornell University and Cornell Tech, in New York City. He also holds a dual appointment in Radiology at Weill Cornell Medicine, where he serves as the Vice Chair of AI and Engineering Research. His group develops machine learning based computational tools for biomedical imaging applications. He is a recipient of an NSF CAREER Award (2018) and an NIH Early Career Development Award (2011).

• 4:00-4:30 pm René Vidal

Trustworthy AI in Health: Foundation Models for Radiology, Cardiology and Autism Diagnosis

René Vidal is the Rachleff and Penn Integrates Knowledge (PIK) University Professor of Electrical and Systems Engineering & Radiology and the Director of the Center for Innovation in Data Engineering and Science (IDEAS) at the University of Pennsylvania. He is also the director of THEORINET, an NSF-Simons Collaboration on the Mathematical Foundations of Deep Learning, an Amazon Scholar and an Affiliated Chief Scientist at NORCE. His current research focuses on the foundations of deep learning and trustworthy AI and its applications in computer vision and biomedical data science. Dr. Vidal is an ACM Fellow, AIMBE Fellow, IEEE Fellow, IAPR Fellow and Sloan Fellow, and has received numerous awards for his work, including the IEEE Edward J. McCluskey Technical Achievement Award, D’Alembert Faculty Award, J.K. Aggarwal Prize, ONR Young Investigator Award, NSF CAREER Award as well as best paper awards in machine learning, computer vision, controls, and medical robotics.

Keynote Speakers 

General Chairs

Scientific Committee 

Organizer Committee