解决医疗影像联邦学习中的罕见病和设备差异问题
Federated Medical Image Classification under Class and Domain Imbalance exploiting Synthetic Sample Generation
- 通过生成合成样本提升稀有病种和不同设备数据的覆盖
- 在多机构数据上显著提升分类准确率与泛化能力
- 适合医疗联邦学习中数据不平衡场景的应用
深度学习在医学影像中的应用面临严峻挑战，包括严格的隐私限制、不同成像设备带来的异构性以及因病理分布不均导致的类别不平衡。本文提出一种新型联邦学习框架 FedSSG，旨在缓解由多种成像设备引起的域偏移，并减轻罕见病种的样本不足问题。核心创新在于生成合成样本并分发至各客户端，以增强对罕见病种和不同设备数据的覆盖。实验表明，该方法在多个异构医疗机构数据上显著提升了模型性能与泛化能力，且客户端计算开销极低。
原文摘要 · Abstract (English)
Exploiting deep learning in medical imaging faces critical challenges, including strict privacy constraints, heterogeneous imaging devices with varying acquisition properties, and class imbalance due to the uneven prevalence of pathologies. In this work, we propose FedSSG, a novel Federated Learning framework that addresses domain shifts caused by diverse imaging devices while mitigating the under-representation of rare pathologies. The key contribution is a strategy for generating synthetic samples and distributing them across clients to improve coverage of both underrepresented pathologies and imaging devices. Experimental results demonstrate that our approach significantly enhances model performance and generalization across heterogeneous institutions, with minimal computational overhead at the client side.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。