Federated training of pathology and radiology models across hospitals

Federated learning has been demonstrated in oncology (for example the multi-national glioblastoma segmentation federation of over 70 sites, and breast-density and pathology consortia), but almost every clinical model is still trained on one or two institutions. The proposal is a persistent federated training infrastructure with secure aggregation, differential privacy options, per-site audit logs and a shared model registry, offered as a public utility to cancer centres.