FLIP is an open-source platform for federated training and evaluation of medical-imaging AI models across healthcare institutions. Models travel to the data held inside each institution; patient data remains within the institution's security boundary.
The platform combines a Central Hub for project orchestration with independently operated Trust nodes. It supports both NVIDIA FLARE and Flower as federated-learning backends. FLIP is developed by the London AI Centre with Guy's and St Thomas' NHS Foundation Trust and King's College London.
For the platform architecture, workflows, deployment guides, and user documentation, start with the FLIP documentation.
| I want to... | Guide |
|---|---|
| Run FLIP on my machine (Central Hub + two example Trusts) | Run FLIP locally for development |
| Deploy the Central Hub on AWS | Deploy the Central Hub — on a Landing Zone Accelerator estate (on AWS (LZA)) |
| Add a Trust to a FLIP network | Deploy a trust node: the shared onboarding runbook, then on a Docker Compose host · on Kubernetes · in a TRE |
| Build or run a federated-learning application | Working with FLIP apps · FL tutorials |
| Contribute to FLIP | CONTRIBUTING.md |
FLIP is maintained as one monorepo. Each major area owns its detailed setup and operational documentation.
| Directory | Responsibility |
|---|---|
flip-api/ |
Central Hub FastAPI service, database, scheduling, and project lifecycle |
flip-ui/ |
Vue 3 web application |
trust/ |
Trust gateway, data and imaging APIs, local OMOP/PACS/XNAT services, and the trust node's deployment shapes (Compose, Helm chart, on-prem Ansible play) |
flip-utils/ |
Shared, pip-installable flip Python library |
fl-services/ |
FLARE and Flower network services, images, and provisioning |
fl-apps/ |
Backend-specific application templates bundled by the Central Hub |
fl-tutorials/ |
Worked federated-learning applications and local runners |
map-apps/ |
MONAI Application Package (MAP) templates for packaging FLIP-trained models for clinical deployment |
deploy/ |
Central Hub Compose files and the AWS provider (Terraform) |
docs/ |
Sphinx source published on ReadTheDocs |
scripts/ |
Repository-wide development and deployment helpers |
If you use FLIP in your research, please cite our paper:
@misc{garciadias2026flip,
title = {Making Cross-Continental Federated Learning Repeatable with {FLIP}: a Multi-Application Study},
author = {Garcia-Dias, Rafael and {Triay Bagur}, Alexandre and Tangwiriyasakul, Chayanin and Fernandez, Virginia and
Esmaeili, Parhom and Ittichaiwong, Piyalitt and Li, Yang and Adams, Lawrence and Buncharoen, Wason and
Chapman, Martin and Chayanond, Benjamaporn and Chunrod, Sadthavud and Fongsri, Tanawat and
Gibson, Kass and Plungprasertkul, Supat and Tangpanithandee, Supawit and Veerakanjana, Kanyakorn and
Goh, Vicky and Antonelli, Michela and Zhang, Joe and Kespechara, Kongkiat and Ourselin, Sebastien and
Cardoso, M. Jorge},
year = {2026},
eprint = {2609.36001},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.36001}
}Contributions are welcome. Please read CONTRIBUTING.md before opening a pull request; commits must include a DCO sign-off. Use GitHub Issues for bugs, feature proposals, and documentation gaps.
For security concerns, follow SECURITY.md rather than opening a public issue.
FLIP is licensed under the Apache License 2.0.