FedDOSE：分解站点效应以建模脑动态功能连接的联邦学习框架
FedDOSE: Federated Learning Framework Decomposing Site Effects for Modeling Brain Dynamic Functional Connectivity
查看机构详情
- Nanyang Technological University（南洋理工大学）
- Shanghai Jiao Tong University（上海交通大学）
- Indian Institute of Technology Ropar（罗帕尔印度理工学院）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
FedDOSE是分解站点效应的联邦学习框架，通过模块化引导Tucker分解等技术处理多站点fMRI的动态功能连接，在ASD和ADHD检测中性能优于现有方法。
中文摘要 AI 辅助
功能磁共振成像（fMRI）数据常被汇集为多站点协作联盟，因为用于分析的深度学习模型需要大量数据集才能良好泛化。联邦学习（FL）提供了一种隐私保护的协作训练范式，但标准方法仍难以应对统计异质性，站点差异是多站点数据场景中的关键挑战。此外，现有的针对fMRI的联邦学习方法依赖静态功能连接（FC），忽略了脑网络中的动态信息。为解决这一问题，我们提出FedDOSE，这是一种显式分解站点差异以分析动态功能连接（dFC）的新框架。FedDOSE引入了模块化引导的Tucker分解模块，用于编码高维dFC张量并高效捕捉模块级时空模式。在所有站点生成类别特定原型，随后通过最优传输（OT）重心公式与Procrustes分析的组合在全局层面对齐。在三个多站点静息态fMRI数据集（ABIDE-I、ABIDE-II和ADHD-200）上进行的自闭症谱系障碍（ASD）和注意缺陷多动障碍（ADHD）诊断的大量实验表明，FedDOSE在ASD和ADHD检测中优于现有最先进方法，其结果凸显了该方法从多站点数据集中学习鲁棒表征以进行可靠分析的有效性。
英文摘要
Functional Magnetic Resonance Imaging ( fMRI ) data are often pooled into collaborative multi-site consortia, as deep learning models for analyses require large datasets to generalize well. While Federated Learning (FL) offers a privacy-preserving paradigm for collaborative training, standard approaches continue to struggle with statistical heterogeneity. In particular, site differences pose a key challenge in multi-site data settings. Additionally, existing FL approaches for fMRI rely on static Functional Connectivity ( FC), omitting dynamic information in brain networks. To address this, we propose FedDOSE, a novel framework that explicitly decomposes site differences for analysis of dynamic FC (dFC). FedDOSE introduces a Modularity-Guided Tucker Decomposition block to encode high-dimensional dFC tensors and capture modular-level spatio-temporal patterns efficiently. Class-specific prototypes are generated across all sites and subsequently aligned at the global level by using a combination of Optimal Transport (OT) barycenter formulation and Procrustes analysis. Extensive experiments for diagnosing Autism Spectrum Disorder (ASD) and Attention-Deficit Hyperactivity Disorder (ADHD) on three multi-site resting-state fMRI datasets: ABIDE-I, ABIDE-II, and ADHD-200, demonstrate that FedDOSE outperforms state-of-the-art methods in ASD and ADHD detection. Our results highlight its effectiveness in learning robust representations from multi-site datasets for reliable analysis.
