The Medical Federated Learning Program

Unlock 1000x more data for medical research with our new research community for federated learning in medical imaging. Scroll for more information ↓

radiologist helping a patient go through a cat scan
map of launched domains

An international initiative with test nodes launched worldwide, this program is a collaboration with researchers from...

University of Oxford logo
Technical University of Munich logo
University of California San Diego logo
Ens de lyon logo
Blockpass Identity Lab logo
University of Pennsylvania logo
Lincoln Laboratory MIT logo
Imperial College London logo
University of Waterloo logo
Emory University logo
Columbia University Logo
Htiti Lab logo
University of Toronto logo
UCLA University of California Los Angeles logo
Georgia Tech University logo
University of Massachusetts Dartmouth logo
QUT Queensland University of Technology logo
Purdue University logo
International Institute of Information Technology Hyderabad logo
UNIFESP Universidade Federal De Sao Paulo logo
University of Vermont logo
Uniklink Koln University Hospital Cologne logo
University of Bristol logo
Universitatea din Craiova logo
Graz University of Technology logo
Health University of Utah logo
University of Calgary logo
Inria French National Institute for Research in Digital Science and Technology logo
German University Cairo logo
Ben-Gurion University of the Negev logo
Complexity Science Hub Vienna Logo
DICLE University logo
Yildiz Technical University logo
Amity University logo
Australian National University logo
Carnegie Mellon University logo
IKIM Universitatsmedizin Essen Institut fur KI in der Medizin logo
Universitats Klinikum Frankfurt Goethe Universitat logo part 2
Goethe University Frankfurt am Main logo
epfl École Polytechnique Fédérale de Lausanne logo
Universitätsklinikum Aachen RWTH Uniklinik logo
Chang Gung Memorial Hospital logo
City University London logo
University of Chicago logo
Télécom Paris Tech logo
KU Leuven logo
Cornell University logo
Boston University computing and data services logo
University of California Irvine logo
CHUV Centre Hospitalier Universitaire Vaudois Lausanne logo
OpenDP logo
Universidade Federal Fluminense logo
Stanford logo
Universite de Montreal logo
NUI Galway OE Gaillimh logo
DKFZ logo german cancer research center
University of Manchester logo
Heidelberg Universitat logo
Medical University Innsbruck logo
University of Bologna logo
KTH logo ventenskap och konst
SciLifeLab Sweden logo
University of Cambridge logo
University of Bath logo
MIT Jameel Clinic logo
Karolinska Institutet logo
Rutgers University logo
Stanford University Center for Artificial Intelligence in Medicine & Imaging logo
Northwestern University logo
Korea Advanced Institute of Science and Technology logo
Queen's University logo
Norwegian University of Science and Technology logo
AI Sweden logo
Vastra Gotalandsregionen Sahlgrenska Universitetssjukhuset logo
Universidad de Alcalá logo
Northeastern University logo
Universitat de Barcelona logo
Istanbul Bilgi Universitesi logo
National University of Singapore Saw Swee Hock School of Public Health logo
SnT University of Luxembourg logo
University of Windsor logo
Koc Universitesi School of Medicine logo
University College Dublin logo
University of Stuttgart logo
University of British Columbia logo
University of Pittsburgh logo
Indraprastha Institute of Technology Delhi logo IIIT-D
Tartu Univ
National Institute of Technology Karnataka, Surathkal logo
EKFZ Digital Health logo
Icahn School of Medicine at Mount Sinai logo
Mila logo
Bilkent University logo
CNRS logo
Institut National Des Sciences Appliquees Lyon logo
University of California Riverside Logo
Universidade Federal do Rio Grande do Norte logo
Indiana University logo
Universitätsklinikum Regensburg Logo
YTU Yildiz Teknik Universitesi logo

Imagine if researchers could perform research using data across hundreds of institutions without needing to acquire a copy of the data.

Today in the field of medical research, far more data exists than any particular researcher is able to use because that data is spread across thousands of medical institutions around the world. Acquiring a copy of the data from another institution is often time consuming, legally burdensome, and expensive for a variety of reasons (privacy, security, IP, competitive advantage, legal limits, to name but a few). As a result, a majority of research is conducted only on data within one or two institutions.

If we could allow researchers to conduct research across institutions without needing to acquire a copy of the data; the costs of data acquisition would decrease, the amount of data used in the typical medical research project would multiply by several orders of magnitude, and a wave of scientific breakthroughs would ensue.

We believe privacy enhancing technologies (PETs) are the key to unlocking cross-institutional collaboration. They have already been shown to facilitate cross-organization scientific collaboration at small scales (2-10 institutions), but  at their core privacy enhancing technologies are partnership enhancing technologies,  which means that they won’t actually unlock orders of magnitude more data in a scientific field until the members of that field have confidence in their efficacy, understand the positive outcomes from their own participation, and acquire the skills to actively create PET-driven data consortiums.

Program Details

The scientific community needs a demonstration of how PETs can create data partnerships at scale (without sharing data) — a template that every scientific discipline can subsequently follow, with significant evidence that this end-to-end partnership procedure is safe, effective, and greatly advantageous for all participants.

We’d like to invite you to participate in OpenMined’s Medical Federated Learning Program, a new program designed to help large numbers of medical researchers meet each other, establish research projects, and demonstrate to the world that they can achieve scientific breakthroughs by pooling their training data using privacy enhancing technologies  (i.e. without sharing data with each other)  for key medical research tasks.

mri scan of head trauma

Phase 01

To help get things started, we are recruiting for our first project, training the most accurate medical classifier to date on the largest-scale federated network yet. The first phase of this project will be educational and  will only use public data that OpenMined provides.  In later phases when you are more comfortable with the technology, we will build into more advanced exercises where you and other participants can bring your own training data.

Key Outcomes

As a participant in The Medical Federated Network you will have a chance to…


Train across 100+ institutions

Be a co-author on the largest-scale federated learning pilot ever executed, and the first federated learning pilot to train across 100+ institutions.


Train the most accurate medical classifier to date

Be a co-author on training the most accurate medical classifier to date, with the chance to definitively solve the task using standard AI techniques applied to orders of magnitude more data.


Learn how to utilize PETs for your own research

Learn hands-on how to take these techniques into your own research, unlocking orders of magnitude more data in your own field of study.

Progress to Date

See progress on The Medical Federated Learning Program's Phase 01


108 Institutions, 123 Nodes

Currently in collaboration with researchers from 108 different institutions. With a total of 123 nodes launched.


Model trained remotely across 100+ nodes"

Were able to train a model across 100 of the domains deployed


4 Open Houses Held

4 Open Houses held with events like speaker presentations, small group discussion, and hands-on PETs experimentation.