Closing the Generalization Gap of Cross-silo Federated Medical Image Segmentation
Closing the Generalization Gap of Cross-silo Federated Medical Image Segmentation
复制标题
DOI：
10.1109/cvpr52688.2022.02020
复制
发表时间：
2022-03
期刊：
影响因子：
--
通讯作者：
An Xu;Wenqi Li;Pengfei Guo;Dong Yang;H. Roth;Ali Hatamizadeh;Can Zhao;Daguang Xu;Heng Huang;Ziyue Xu-
中科院分区：
文献类型：
--
作者：
An Xu;Wenqi Li;Pengfei Guo;Dong Yang;H. Roth;Ali Hatamizadeh;Can Zhao;Daguang Xu;Heng Huang;Ziyue Xu-
近年来，跨筒仓联邦学习（FL）在深度学习的医学成像分析中引起了广泛关注，因为它可以解决数据不足，数据隐私和训练效率等关键问题。然而，从FL训练的模型和从集中式训练的模型之间可能存在泛化差距。这个重要的问题来自参与客户端中本地数据的非iid数据分布，称为客户端漂移。在这项工作中，我们提出了一种新的训练框架FedSM，以避免客户端漂移问题，并成功地关闭了泛化差距相比，集中式训练的医学图像分割任务的第一次。我们还提出了一种新的个性化FL目标制定和一种新的方法SoftPull来解决它在我们提出的框架FedSM。我们进行了严格的理论分析，以保证其收敛性优化非凸光滑的目标函数。使用深度FL的真实世界医学图像分割实验验证了我们所提出的方法的动机和有效性。
Cross-silo federated learning (FL) has attracted much attention in medical imaging analysis with deep learning in recent years as it can resolve the critical issues of insufficient data, data privacy, and training efficiency. However, there can be a generalization gap between the model trained from FL and the one from centralized training. This important issue comes from the non-iid data distribution of the local data in the participating clients and is well-known as client drift. In this work, we propose a novel training frame-work FedSM to avoid the client drift issue and successfully close the generalization gap compared with the centralized training for medical image segmentation tasks for the first time. We also propose a novel personalized FL objective formulation and a new method SoftPull to solve it in our proposed framework FedSM. We conduct rigorous theoretical analysis to guarantee its convergence for optimizing the non-convex smooth objective function. Real-world medical image segmentation experiments using deep FL validate the motivations and effectiveness of our proposed method.