A Federated Learning Framework for Handling Subtype Confounding and Heterogeneity in Large-Scale Neuroimaging Diagnosis

TL;DR

This paper introduces a federated learning framework for neuroimaging diagnosis that effectively manages subtype heterogeneity and confounding factors, improving accuracy and robustness across large, diverse datasets.

Contribution

It presents a novel federated learning approach with dynamic navigation and meta-integration modules tailored for neuroimaging CAD systems, addressing heterogeneity and confounding.

Findings

Achieved 74.06% average accuracy across multiple sites.

Significant improvements over traditional methods in diagnostic accuracy.

Validated the importance of navigation and meta-integration modules.

Abstract

Computer-aided diagnosis (CAD) systems play a crucial role in analyzing neuroimaging data for neurological and psychiatric disorders. However, small-sample studies suffer from low reproducibility, while large-scale datasets introduce confounding heterogeneity due to multiple disease subtypes being labeled under a single category. To address these challenges, we propose a novel federated learning framework tailored for neuroimaging CAD systems. Our approach includes a dynamic navigation module that routes samples to the most suitable local models based on latent subtype representations, and a meta-integration module that combines predictions from heterogeneous local models into a unified diagnostic output. We evaluated our framework using a comprehensive dataset comprising fMRI data from over 1300 MDD patients and 1100 healthy controls across multiple study cohorts. Experimental results demonstrate significant improvements in diagnostic accuracy and robustness compared to traditional methods. Specifically, our framework achieved an average accuracy of 74.06\% across all tested sites, showcasing its effectiveness in handling subtype heterogeneity and enhancing model generalizability. Ablation studies further confirmed the importance of both the dynamic navigation and meta-integration modules in improving performance. By addressing data heterogeneity and subtype confounding, our framework advances reliable and reproducible neuroimaging CAD systems, offering significant potential for personalized medicine and clinical decision-making in neurology and psychiatry.