Decentralized Personalization for Federated Medical Image Segmentation via Gossip Contrastive Mutual Learning

Federated Learning (FL) presents a promising avenue for collaborative model training among medical centers, facilitating knowledge exchange without compromising data privacy. However, vanilla FL is prone to server failures and rarely achieves optimal performance on all participating sites due to heterogeneous data distributions among them. To overcome these challenges, we propose Gossip Contrastive Mutual Learning (GCML), a unified framework to optimize personalized models in a decentralized environment, where Gossip Protocol is employed for flexible and robust peer-to-peer communication. To make efficient and reliable knowledge exchange in each communication without the global knowledge across all the sites, we introduce deep contrast mutual learning (DCML), a simple yet effective scheme to encourage knowledge transfer between the incoming and local models through collaborative training on local data. By integrating DCML with other efforts to optimize site-specific models by leveraging useful information from peers, we evaluated the performance and efficiency of the proposed method on three publicly available datasets with different segmentation tasks. Our extensive experimental results show that the proposed GCML framework outperformed both centralized and decentralized FL methods with significantly reduced communication overhead, indicating its potential for real-world deployment.