Federated learning (FL) for histopathology image segmentation involving multiple medical sites plays a crucial role in advancing the field of accurate disease diagnosis and treatment. However, it is still a task of great challenges due to the sample imbalance across clients and large data heterogeneity from disparate organs, variable segmentation tasks, and diverse distribution. Thus, we propose a novel FL approach for histopathology nuclei and tissue segmentation, FedSODA, via synthetic-driven cross-assessment operation (SO) and dynamic stratified-layer aggregation (DA). Our SO constructs a cross-assessment strategy to connect clients and mitigate the representation bias under sample imbalance. Our DA utilizes layer-wise interaction and dynamic aggregation to diminish heterogeneity and enhance generalization. The effectiveness of our FedSODA has been evaluated on the most extensive histopathology image segmentation dataset from 7 independent datasets. The code is available at https://github.com/yuanzhang7/FedSODA.
@article{arxiv.2312.12824,
title = {FedSODA: Federated Cross-assessment and Dynamic Aggregation for Histopathology Segmentation},
author = {Yuan Zhang and Yaolei Qi and Xiaoming Qi and Lotfi Senhadji and Yongyue Wei and Feng Chen and Guanyu Yang},
journal= {arXiv preprint arXiv:2312.12824},
year = {2023}
}