Federated learning for Heart Segmentation

Training deep learning models for medical imaging requires access to large volumes of sensitive patient data. To this end, the models are generally trained on centralized, de-identified databases that are hard to collect because of privacy requirements. Federated learning proposes an alternative approach, in which a coalition of hospitals collaboratively trains a central model without exchanging any clinical data. This paper explores the combination of federated learning with U-Net models, and applies it to the task of image segmentation of the heart. A variant of federated learning referred to as "federated equal-chances" that improves segmentation performance on unbalanced datasets is introduced as well.