{"entity":{"id":"idea-data-federated-learning-imaging","kind":"idea","name":"Federated training of pathology and radiology models across hospitals","aka":[],"tldr":"Train one AI on pathology slides and radiology scans from dozens of hospitals without any hospital sharing its images: the model travels to the data. Federated learning has worked for glioblastoma segmentation across 70-plus sites, yet almost every clinical model is still trained at one or two institutions, so a persistent shared training infrastructure is proposed.","summary":"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.","asOf":"2026-09-08","links":[{"label":"Federated learning for glioblastoma (Pati et al. 2022)","url":"https://www.nature.com/articles/s41467-022-33407-5"}],"tags":[],"related":[],"cancers":[],"sections":["ai-computation"],"technologies":["digital-pathology-ai","pathology-foundation-model","radiology-ai-screening"],"targets":[],"drugs":[],"companies":["owkin"],"institutions":[],"pathways":[],"terms":[],"trials":[],"people":[],"bottlenecks":["b-data-silos","b-ai-validation"],"keyPapers":[],"journals":[],"dependsOn":[],"notes":[],"hypothesis":"Models trained federatedly across 20 or more sites will generalise to unseen hospitals with less than half the performance drop of single-site models, measured on a sequestered multi-site test set.","rationale":"The largest published federated study (Pati et al., Nature Communications 2022) improved out-of-sample glioblastoma segmentation by a third versus a public-data model. Generalisation failure is the main reason cancer AI does not survive deployment.","test":"Train a pathology model for a standard task (for example mitotic count or HER2 scoring) both centrally on one large site and federatedly across 10 sites; evaluate both on five held-out hospitals in other countries.","maturity":"early-clinical","actor":"engineering","cost":"medium","horizonYears":3},"route":"/ideas/idea-data-federated-learning-imaging/","neighbours":{"section":[{"id":"ai-computation","kind":"section","name":"AI & Computation","route":"/fronts/ai-computation/"}],"technology":[{"id":"radiology-ai-screening","kind":"technology","name":"AI in radiology","route":"/technologies/radiology-ai-screening/"},{"id":"digital-pathology-ai","kind":"technology","name":"Digital pathology & AI","route":"/technologies/digital-pathology-ai/"},{"id":"pathology-foundation-model","kind":"technology","name":"Pathology & radiology foundation models","route":"/technologies/pathology-foundation-model/"}],"company":[{"id":"owkin","kind":"company","name":"Owkin","route":"/companies/owkin/"}],"bottleneck":[{"id":"b-ai-validation","kind":"bottleneck","name":"AI that is built but not validated or deployed","route":"/bottlenecks/b-ai-validation/"},{"id":"b-data-silos","kind":"bottleneck","name":"Data silos","route":"/bottlenecks/b-data-silos/"}],"idea":[{"id":"idea-data-precompetitive-cancer-foundation-model","kind":"idea","name":"A pre-competitive consortium to train a shared multimodal cancer foundation model","route":"/ideas/idea-data-precompetitive-cancer-foundation-model/"}]}}