Source-Free Collaborative Domain Adaptation via Multi-Perspective Feature Enrichment for Functional MRI Analysis

TL;DR

This paper introduces a source-free collaborative domain adaptation framework with multi-perspective feature enrichment for analyzing multi-site resting-state fMRI data, effectively addressing cross-site heterogeneity without source data access.

Contribution

It proposes a novel source-free adaptation method using multi-view feature enrichment and mutual consistency constraints, enabling effective cross-site fMRI analysis without source data.

Findings

Improved cross-scanner prediction accuracy on multiple datasets.

Effective feature representation learned through unsupervised pretraining.

Model pretrained on large-scale data enhances generalization.

Abstract

Resting-state functional MRI (rs-fMRI) is increasingly employed in multi-site research to aid neurological disorder analysis. Existing studies usually suffer from significant cross-site/domain data heterogeneity caused by site effects such as differences in scanners/protocols. Many methods have been proposed to reduce fMRI heterogeneity between source and target domains, heavily relying on the availability of source data. But acquiring source data is challenging due to privacy concerns and/or data storage burdens in multi-site studies. To this end, we design a source-free collaborative domain adaptation (SCDA) framework for fMRI analysis, where only a pretrained source model and unlabeled target data are accessible. Specifically, a multi-perspective feature enrichment method (MFE) is developed for target fMRI analysis, consisting of multiple collaborative branches to dynamically capture fMRI features of unlabeled target data from multiple views. Each branch has a data-feeding module, a spatiotemporal feature encoder, and a class predictor. A mutual-consistency constraint is designed to encourage pair-wise consistency of latent features of the same input generated from these branches for robust representation learning. To facilitate efficient cross-domain knowledge transfer without source data, we initialize MFE using parameters of a pretrained source model. We also introduce an unsupervised pretraining strategy using 3,806 unlabeled fMRIs from three large-scale auxiliary databases, aiming to obtain a general feature encoder. Experimental results on three public datasets and one private dataset demonstrate the efficacy of our method in cross-scanner and cross-study prediction tasks. The model pretrained on large-scale rs-fMRI data has been released to the public.