The authors developed FedFMS to address the challenges of training foundation models for medical image segmentation in a federated learning framework. Their approach involved creating Federated SAM (FedSAM) and a communication-efficient FedSAM with Medical SAM Adapter (FedMSA).
Medical image segmentation foundation models can be effectively deployed in a federated learning framework, maintaining performance and privacy.
Federated Foundation Models (FedFMS) ermöglichen effiziente medizinische Bildsegmentierung und Training.
Federated Foundation Models (FFMs) kombinieren die Vorteile von Foundation Models (FMs) und Federated Learning (FL), um datenschutzfreundliches und kollaboratives Lernen über mehrere Endnutzer hinweg zu ermöglichen.