# Classifying Major Depressive Disorder Using Multimodal MRI Data: A Personalized Federated Algorithm

## TL;DR

This paper introduces a privacy-preserving algorithm for diagnosing major depressive disorder using MRI data from multiple sites without sharing raw data.

## Contribution

The novel pF-GMCO algorithm combines gradient matching, contrastive learning, and multimodal pooling for federated MDD classification.

## Key findings

- pF-GMCO achieved 79.07% accuracy on the Rest-Meta-MDD dataset with 2293 subjects from 23 sites.
- The method outperforms existing approaches in handling domain shift and integrating multimodal MRI data.

## Abstract

Background: Neuroimaging-based diagnostic approaches are of critical importance for the accurate diagnosis and treatment of major depressive disorder (MDD). However, multisite neuroimaging data often exhibit substantial heterogeneity in terms of scanner protocols and population characteristics. Moreover, concerns over data ownership, security, and privacy make raw MRI datasets from multiple sites inaccessible, posing significant challenges to the development of robust diagnostic models. Federated learning (FL) offers a privacy-preserving solution to facilitate collaborative model training across sites without sharing raw data. Methods: In this study, we propose the personalized Federated Gradient Matching and Contrastive Optimization (pF-GMCO) algorithm to address domain shift and support scalable MDD classification using multimodal MRI. Our method incorporates gradient matching based on cosine similarity to weight contributions from different sites adaptively, contrastive learning to promote client-specific model optimization, and multimodal compact bilinear (MCB) pooling to effectively integrate structural MRI (sMRI) and functional MRI (fMRI) features. Results and Conclusions: Evaluated on the Rest-Meta-MDD dataset with 2293 subjects from 23 sites, pF-GMCO achieved accuracy of 79.07%, demonstrating superior performance and interpretability. This work provides an effective and privacy-aware framework for multisite MDD diagnosis using federated learning.