[论文解读] The Federated Tumor Segmentation (FeTS) Challenge

Sarthak Pati, Ujjwal Baid+30 more|arXiv (Cornell University)|May 12, 2021

Radiomics and Machine Learning in Medical Imaging参考文献 45被引用 42

一句话总结

描述 FeTS 2021 联邦学习挑战在脑肿瘤分割中的应用，包含两个任务：联邦权重聚合和在跨多机构数据、不共享患者数据的情况下进行的野外联邦评估。

ABSTRACT

This manuscript describes the first challenge on Federated Learning, namely the Federated Tumor Segmentation (FeTS) challenge 2021. International challenges have become the standard for validation of biomedical image analysis methods. However, the actual performance of participating (even the winning) algorithms on "real-world" clinical data often remains unclear, as the data included in challenges are usually acquired in very controlled settings at few institutions. The seemingly obvious solution of just collecting increasingly more data from more institutions in such challenges does not scale well due to privacy and ownership hurdles. Towards alleviating these concerns, we are proposing the FeTS challenge 2021 to cater towards both the development and the evaluation of models for the segmentation of intrinsically heterogeneous (in appearance, shape, and histology) brain tumors, namely gliomas. Specifically, the FeTS 2021 challenge uses clinically acquired, multi-institutional magnetic resonance imaging (MRI) scans from the BraTS 2020 challenge, as well as from various remote independent institutions included in the collaborative network of a real-world federation (https://www.fets.ai/). The goals of the FeTS challenge are directly represented by the two included tasks: 1) the identification of the optimal weight aggregation approach towards the training of a consensus model that has gained knowledge via federated learning from multiple geographically distinct institutions, while their data are always retained within each institution, and 2) the federated evaluation of the generalizability of brain tumor segmentation models "in the wild", i.e. on data from institutional distributions that were not part of the training datasets.

研究动机与目标

• 在地理上分布不同的机构中，利用联邦学习激励和实现鲁棒的脑肿瘤分割，同时保护数据隐私。
• 在不进行数据汇聚的情况下，识别用于共识模型构建的有效联邦权重聚合策略。
• 通过跨机构的联邦评估，在现实世界分布变化下评估模型的泛化能力。
• 提供标准化的数据集、预处理和标注协议，以支持可重复的基于FL的分割研究。

提出的方法

• 使用来自 BraTS 2020 和 FeTS 联邦的多机构 mpMRI 数据及肿瘤亚区的真实标签。
• 应用带残差连接的固定 U-Net 结构，以将关注点放在聚合方法评估上，而非分割架构。
• 将训练组织为联邦轮次，合作者在本地训练并将更新发送给中心聚合器以创建共识模型。
• 评估聚合策略和通信效率，包括对网络中断（落后节点）的可选处理。
• 在每个机构保留的联邦测试数据上进行评估，从而在多样化领域实现野外泛化评估。
• 以 Dice 相似系数和鲁棒的 95 百分位数 Hausdorff 距离来衡量分割质量；将通信预算作为基于轮次的成本进行监控。

实验结果

研究问题

• RQ1 在跨机构对本地训练模型的知识进行聚合以形成鲁棒的共识分割模型方面，最佳方法是什么？
• RQ2 联邦分割模型对训练集中未代表的机构数据的泛化能力有多好（野外的领域泛化）？
• RQ3 通信效率和对中断的处理在此环境下如何影响联邦学习性能？

主要发现

• 本手稿介绍了首个联邦学习脑肿瘤分割挑战，并概述了用于FL权重聚合和联邦评估的两个具体任务。
• 评估以 Dice 相似系数和 95 百分位 Hausdorff 距离作为主要分割指标。
• 使用带残差连接的固定 U-Net，以隔离联合方法对性能的影响。
• 预处理遵循 BraTS 流程，包括配准和脑部提取，使用公开的 CaPTk 和 FeTS 工具。
• 用于可重复性的代码和流水线通过 CaPTk 和 FeTS 仓库发布。
• 挑战框架强调隐私保护、分布式评估，数据保留在本地站点。