Skip to the content.

Federated Learning for Healthcare

Welcome to the Federated Learning tutorial that will be run in conjunction with the MICCAI conference!

Federated Learning (FL) is increasingly important in privacy sensitive domains, such as healthcare, where sharing of private/patient data is a barrier to building models that generalize well in the real world and minimize bias.

In 2021, we led the largest real world federation, with a network of 59 healthcare institutions around the world. Furthermore, leveraging the collaborators of this real-world FL initiative, we led the first ever FL challenge, focusing on the tumor segmentation task, called The FeTS 2021 challenge. Taking into consideration the value and the interest of the community in this new paradigm for data private multi-institutional collaborations and building upon our experience, we organize this tutorial on FL for healthcare.

The tutorial will teach you how to use state-of-the-art open-source Python library for Federated Learning OpenFL.

When and Where?

September 22nd from 11:50 to 15:20 (SGT time)

Sign up as a virtual tutorial attendee until the day of the event at the MICCAI Registration Page

Organizing Committee

Tutorial Description

The aim of this tutorial is to facilitate education on how to perform Federated Learning on both simulated and realworld studies. Tutorial structure focuses on specific clearly indicated parts for beginners and for more advanced attendees. Data scientists of different medical imaging communities (e.g., radiology, pathology) are considered during this tutorial on the opportunities and challenges in developing and using FL fortraining Al models acrossinstitutions using privacy preserving techniques. We plan on covering a spectrum of techniques, from software-based approaches that can be considered a method or a metric (e.g., differential privacy), to hardware-based trusted execution computing environments (TEEs).

The motivation for the tutorial is driven by the need to train and validate deep learning models across data silos, to create models that gain knowledge from diverse patient populations and hence generalize well, mitigate bias, and pave the way towards addressing health disparities.

Preliminary program

Part I (45 minutes, environment setup)

Part II (45 minutes, lecture based)

Part III (~2h, Hands on)

Data Scientists and Computational Scientists attending this tutorial will be able to adapt their existing centralized algorithms to a federated architecture or build new models. Non-data scientists (e.g., more clinically-oriented attendees of the CLINICAI sessions) will learn about both technical and non-technical considerations setting up federations for training medical Al models. Importantly, attendees will also understand the privacy and security attack vectors and mitigations when using FL.



Half day (afternoon), Hands-on


In favor of open science, transparency, and further communicating the information presented during the tutorial beyond its actual lifecycle during MICCAI 2021, we intend to produce tutorial notes and be part of the MICCAI satellite event proceedings.