The workshop was featured in the BEST OF CVPR of Computer Vision News

Workshop Schedule

Tentative schedule. Listed times are in Pacific Daylight Time

8:00 AM Welcome and Opening Remarks

Moderators: Tal Arbel and Yuyin Zhou (on-site)

8:00 AM - 10:00 AM Morning Session 1

Moderators: Nicolas Padoy (online), Tal Arbel and Yuyin Zhou (on-site)

  "Exploring Foundation Models for Generalist Medical AI". Shekoofeh Azizi, Google DeepMind (in person)
  "Cognitive Vision for Surgical Guidance during Cancer Resection". Stamatia Giannarou, Imperial College London (virtual)
  "Federated, secure and auditable AI for medical imaging applications". Marco Lorenzi, INRIA (virtual)
  "Generative GNNs in Connectomics". Islem Rekik, Imperial College London (virtual)
10:00 AM - 10:30 AM Coffee Break
10:30 AM - 12:30 AM Morning Session 2

Moderators: Vasileios Belagiannis (online), Tal Arbel and Yuyin Zhou (on-site)

  "Medical computer vision to advance fetal ultrasound use in LMICs healthcare settings". Alison Noble, University of Oxford (in person)
  "Generating synthetic images and videos for data augmentation and sharing in medical applications". Sharon Xiaolei Huang, Penn State University (in person)
  "Complementing Surgeons with Situation Awareness using Computer Vision". Duygu Sarikaya, University of Leeds (virtual)
  "Annotations at Scale for the creation of AI solutions in healthcare". Chen Sagiv, DeePathology.ai, SagivTech & CAIO SurgeonAI (virtual)
12:30 PM - 1:30 PM Lunch Break
1:30 PM - 4:00 PM Afternoon Session

Moderators: Mert Sabuncu (online), Tal Arbel and Yuyin Zhou (on-site)

  "Bias and confounders in medical studies in the age of large-scale models". Ehsan Adeli, Stanford University (in person)
  "Surgical motion understanding and generation towards augmented minimally invasive robotic procedures". Hongliang Ren, Chinese University of Hong Kong (in person)
  "Towards Data-efficient learning for long surgical video analysis". Muhammad Abdullah Jamal, Intuitive Surgical (virtual)
  "Explainable AI for improved fetal ultrasound diagnostics". Aasa Feragen, Technical University of Denmark (virtual)
  Vishal M. Patel, Johns Hopkins University (virtual)

About the workshop

Overview

The CVPR MCV workshop provides a unique forum for researchers and developers in academia, industry and healthcare to present, discuss and learn about cutting-edge advances in machine learning and computer vision for medical image analysis and computer assisted interventions. The workshop offers a venue for potential new collaborative efforts, encouraging more dataset and information exchanges for important clinical applications.

The ultimate goal of the MCV workshop is to bring together stakeholders interested in leveraging medical imaging data, machine learning and computer vision algorithms to build the next generation of tools and products to advance image-based healthcare. It is time to deliver!

The program features invited talks from leading researchers from academia and industry and clinicians. There will be no paper submissions at this year's workshop.

About

This workshop will serve to bridge the gap between the medical image analysis and computer aided intervention communities and the computer vision communities, providing a forum for exchanging ideas and potential new collaborative efforts, encouraging more data sharing, advocating for radiology image database building and information exchange on machine learning and computer vision frameworks in the context of medical image analysis. This collective effort among peers will facilitate the next level of large scale statistical learning, especially deep learning.

We invite leading clinician-researchers who actively practice medicine to share their work, perspectives, experiences and expectations. Our workshop will serve as a forum to forge connections with computer vision, medical imaging researchers and clinical key opinion leaders. It is time to deliver!

Learning or statistical learning based methodology has been a popular topic at recent MICCAI conferences. Deep learning (CNNs, transformers, diffusion models, among many others) has revolutionized the field of computer vision, but is only beginning to make significant advances in medical image analysis. To move it forward, in addition to a shortage of large, annotated datasets, development of new computer vision representations and frameworks are needed to address the particular needs of the medical communities. The challenges of the developing new image representations stems from the issue of data sparsity in medical imaging, requiring the decomposition of 3D image volumes into 2D or 2.5D views (regularly or randomly sampled) with spatial aggregation of local decisions. This workshop will cover all topics of large scale or novel statistical and deep learning in medical imaging, via a series of 30 minute invited talks from researchers working in both fields. We believe that we have an excellent list of confirmed and tentative speakers, from academia to industry and clinical KOLs, who will present work ranging from the more theoretical to the more applied.

The ultimate goal is leveraging big data, deep learning and novel representation to effectively build the next generation of robust quantitative medical imaging parsing tools products. For example, a large-scale imaging based cancer screening tool with very high patient-level performance will be clinically valuable, but is quite challenging technically (high sensitivity but ultra-low false positive rate on classifying patients as with or without certain cancers). Other applications include computational 3D reconstruction, computer vision for medical robotics, bias and fairness in healthcare AI, among many other emerging topics

Confirmed Speakers

In-person

...

Ehsan Adeli

Stanford University

...

Shekoofeh Azizi

Google DeepMind

...

Stamatia Giannarou

Imperial College London

...

Sharon Xiaolei Huang

Penn State University

...

Muhammad Abdullah Jamal

Intuitive Surgical

...

Alison Noble

University of Oxford

...

Hongliang Ren

Chinese University of Hong Kong

Virtual

...

Aasa Feragen

Technical University of Denmark

...

Marco Lorenzi

INRIA

...

Vishal M. Patel

Johns Hopkins University

...

Islem Rekik

Imperial College London

...

Chen Sagiv

DeePathology.ai, SagivTech & CAIO SurgeonAI

...

Duygu Sarikaya

University of Leeds

Organizers

...

Tal Arbel

McGill University

...

Ayelet Akselrod-Balin

Reichman University

...

Vasileios Belagiannis

Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU)

...

Qi Dou

Chinese University of Hong Kong

...

Moti Freiman

Technion - Israel Institute of Technology

...

Nicolas Padoy

University of Strasbourg & IHU Strasbourg

...

Tammy Riklin-Raviv

Ben-Gurion University

...

Mathias Unberath

Johns Hopkins University

...

Yuyin Zhou

University of California, Santa Cruz

...

Mert Sabuncu

Cornell University

Contact