Federated learning (FL) has emerged as a promising strategy for
collaboratively training complicated machine learning models from different
medical centers without the need of data sharing. However, the traditional FL
relies on a central server to orchestrate the global model training among
clients. This makes it vulnerable to the failure of the model server.
Meanwhile, the model trained based on the global data property may not yield
the best performance on the local data of a particular site due to the
variations of data characteristics among them. To address these limitations, we
proposed Gossip Mutual Learning(GML), a decentralized collaborative learning
framework that employs Gossip Protocol for direct peer-to-peer communication
and encourages each site to optimize its local model by leveraging useful
information from peers through mutual learning. On the task of tumor
segmentation on PET/CT images using HECKTOR21 dataset with 223 cases from five
clinical sites, we demonstrated GML could improve tumor segmentation
performance in terms of Dice Similarity Coefficient (DSC) by 3.2%, 4.6% and
10.4% on site-specific testing cases as compared to three baseline methods:
pooled training, FedAvg and individual training, respectively. We also showed
GML has comparable generalization performance as pooled training and FedAvg
when applying them on 78 cases from two out-of-sample sites where no case was
used for model training. In our experimental setup, GML showcased a sixfold
decrease in communication overhead compared to FedAvg, requiring only 16.67% of
the total communication overhead.

GML 是一种去中心化的协作学习框架，通过使用八卦协议实现直接的点对点通信并利用相互学习从同行处获取有用信息，改善了基于全局数据特性训练的模型性能，尤其在肿瘤分割任务方面，相比于基线方法（汇集训练、FedAvg 和单独训练），在特定测试样本中的 Dice 相似系数（DSC）分别提高了 3.2%、4.6% 和 10.4%，在 78 个样本的两个样本外站点上应用时，GML 的泛化性能与汇集训练和 FedAvg 相当，同时通信开销减少了六倍，仅需总通信开销的 16.67%。