FedSDA：面向非独立同分布组织病理图像分类的联邦染色分布对齐方法
FedSDA: Federated Stain Distribution Alignment for Non-IID Histopathological Image Classification
AI总结：
针对联邦学习下组织病理图像非独立同分布导致的分布偏移问题，本文提出FedSDA方法，通过染色分布对齐缓解偏移且规避隐私风险，实验证明其性能优于同类基线，可为计算病理领域提供实用参考。
摘要：
联邦学习（FL）已实现了在不直接共享隐私敏感训练数据的前提下，于去中心化数据资源间协同训练模型的目标。尽管近期取得了诸多进展，但非独立同分布（non-IID）数据带来了不可避免的挑战，阻碍了联邦学习的落地应用。本研究从一个此前仅获得有限关注的直观视角，解决存在特征分布偏移的非独立同分布组织病理图像问题。具体而言，我们从数据分布角度切入，仅通过调整所有客户端的数据分布来应对该问题。依托扩散模型在拟合数据分布方面的成功经验，同时利用染色分离技术提取与组织病理图像非独立同分布特性密切相关的关键特征，我们提出了联邦染色分布对齐（Federated Stain Distribution Alignment, FedSDA）方法。FedSDA在联邦学习框架下将每个客户端的染色分布与目标分布对齐，以缓解客户端间的分布偏移问题。此外，考虑到已有研究表明在联邦学习场景下基于原始数据训练扩散模型易存在隐私泄露风险，我们在有效实现分布对齐的同时规避了该问题。大量实验结果显示，FedSDA不仅能有效提升那些聚焦于缓解客户端模型更新差异的基线方法的性能，还优于从数据分布角度解决非独立同分布数据问题的基线方法。我们证明FedSDA可为计算病理学领域提供有价值的实用思路。
英文摘要：
Federated learning (FL) has shown success in collaboratively training a model among decentralized data resources without directly sharing privacy-sensitive training data. Despite recent advances, non-IID (non-independent and identically distributed) data poses an inevitable challenge that hinders the use of FL. In this work, we address the issue of non-IID histopathological images with feature distribution shifts from an intuitive perspective that has only received limited attention. Specifically, we address this issue from the perspective of data distribution by solely adjusting the data distributions of all clients. Building on the success of diffusion models in fitting data distributions and leveraging stain separation to extract the pivotal features that are closely related to the non-IID properties of histopathological images, we propose a Federated Stain Distribution Alignment (FedSDA) method. FedSDA aligns the stain distribution of each client with a target distribution in an FL framework to mitigate distribution shifts among clients. Furthermore, considering that training diffusion models on raw data in FL has been shown to be susceptible to privacy leakage risks, we circumvent this problem while still effectively achieving alignment. Extensive experimental results show that FedSDA is not only effective in improving baselines that focus on mitigating disparities across clients' model updates but also outperforms baselines that address the non-IID data issues from the perspective of data distribution. We show that FedSDA provides valuable and practical insights for the computational pathology community.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
