Adversarial Versus Federated: An Adversarial Learning based Multi-Modality Cross-Domain Federated Medical Segmentation
This work addresses data heterogeneity in federated medical segmentation, enabling single-modality clients to process cross-modality data, which is incremental as it builds on existing federated learning and domain adaptation techniques.
The paper tackles the challenge of cross-domain medical image segmentation in federated learning where clients have different image modalities, proposing a Federated Domain Adaptation (FedDA) framework that uses adversarial learning to align features across clients, achieving robust performance compared to state-of-the-art methods in objective and subjective assessments.
Federated learning enables collaborative training of machine learning models among different clients while ensuring data privacy, emerging as the mainstream for breaking data silos in the healthcare domain. However, the imbalance of medical resources, data corruption or improper data preservation may lead to a situation where different clients possess medical images of different modality. This heterogeneity poses a significant challenge for cross-domain medical image segmentation within the federated learning framework. To address this challenge, we propose a new Federated Domain Adaptation (FedDA) segmentation training framework. Specifically, we propose a feature-level adversarial learning among clients by aligning feature maps across clients through embedding an adversarial training mechanism. This design can enhance the model's generalization on multiple domains and alleviate the negative impact from domain-shift. Comprehensive experiments on three medical image datasets demonstrate that our proposed FedDA substantially achieves cross-domain federated aggregation, endowing single modality client with cross-modality processing capabilities, and consistently delivers robust performance compared to state-of-the-art federated aggregation algorithms in objective and subjective assessment. Our code are available at https://github.com/GGbond-study/FedDA.