[论文解读] FedDis: Disentangled Federated Learning for Unsupervised Brain Pathology Segmentation

Cosmin I. Bercea, Benedikt Wiestler+2 more|arXiv (Cornell University)|Mar 5, 2021

Medical Imaging and Analysis被引用 25

一句话总结

FedDis 将模型参数分解为形状与外观，在联邦学习中仅共享形状以缓解非IID域偏移，并在多数据集上实现改进的无监督脑病理分割。

ABSTRACT

In recent years, data-driven machine learning (ML) methods have revolutionized the computer vision community by providing novel efficient solutions to many unsolved (medical) image analysis problems. However, due to the increasing privacy concerns and data fragmentation on many different sites, existing medical data are not fully utilized, thus limiting the potential of ML. Federated learning (FL) enables multiple parties to collaboratively train a ML model without exchanging local data. However, data heterogeneity (non-IID) among the distributed clients is yet a challenge. To this end, we propose a novel federated method, denoted Federated Disentanglement (FedDis), to disentangle the parameter space into shape and appearance, and only share the shape parameter with the clients. FedDis is based on the assumption that the anatomical structure in brain MRI images is similar across multiple institutions, and sharing the shape knowledge would be beneficial in anomaly detection. In this paper, we leverage healthy brain scans of 623 subjects from multiple sites with real data (OASIS, ADNI) in a privacy-preserving fashion to learn a model of normal anatomy, that allows to segment abnormal structures. We demonstrate a superior performance of FedDis on real pathological databases containing 109 subjects; two publicly available MS Lesions (MSLUB, MSISBI), and an in-house database with MS and Glioblastoma (MSI and GBI). FedDis achieved an average dice performance of 0.38, outperforming the state-of-the-art (SOTA) auto-encoder by 42% and the SOTA federated method by 11%. Further, we illustrate that FedDis learns a shape embedding that is orthogonal to the appearance and consistent under different intensity augmentations.

研究动机与目标

• 促进跨多机构的隐私保护学习用于脑病理分割。
• 提出 FedDis 以解缠形状与外观，并仅共享形状参数。
• 在真实病理数据集上展示改进的异常分割性能。
• 证明 FedDis 学习到的形状嵌入与外观正交且对强度变化具有鲁棒性。

提出的方法

• 将形状与外观参数分离的解缠编码器架构。
• 联邦训练中，全局聚合仅对各客户端的形状参数进行平均。
• 潜在对比损失 LCL，用以通过 KL 散度项在形状与外观之间实现形状一致性（SCL）和潜在正交性（LOL），以及潜在对比约束。
• 基于重构的无监督异常分割，使用残差 x - x_rec 作为异常证据。
• 超参数：alpha 用于重构与 LCL 平衡；beta 在 LCL 内对 SCL 与 LOL 的加权；gamma-shift 增强用于形状一致性。

实验结果

研究问题

• RQ1 通过解缠形状与外观，FedDis 是否能在联邦无监督脑异常分割中缓解跨站点的域偏移？
• RQ2 仅共享形状参数是否相对于标准联邦方法提高了对未知扫描仪和数据集的泛化能力？
• RQ3 潜在表征是否呈现出与外观正交且对强度变化具有鲁棒性的形状嵌入？
• RQ4 潜在对比损失分量（SCL 与 LOL）对分割性能与解缠的影响？

主要发现

• FedDis 在主要异常分割任务上达到平均 Dice 分数 0.38，超越 SOTA 自编码器 42%，以及 SOTA 联邦方法 11%。
• FedDis 在实际病理数据集上优于包括 FedAvg、FedVC、SiloBN 与 FedGN 在内的若干基线。
• FedDis 学习到的形状嵌入与外观正交且在强度变化下稳定，如潜在分析与消融所示。
• 消融实验表明潜在对比损失对有效解缠和性能提升至关重要。
• 相较于数据集中训练，FedDis 在隐私保护分布式数据条件下提供强劲的分割性能。