Learning Robust Hierarchical Patterns of Human Brain across Many fMRI Studies

TL;DR

This paper proposes a matrix factorization and adversarial learning approach to improve the estimation and reproducibility of hierarchical brain connectivity patterns in multi-site fMRI data, accounting for site-related variations.

Contribution

It introduces a novel matrix factorization method combined with adversarial learning to reduce site effects and enhance reproducibility in multi-site fMRI analysis.

Findings

Improved accuracy in estimating brain connectivity components.

Enhanced reproducibility of components across different sites.

Preservation of biologically relevant variations such as age-related differences.

Abstract

Resting-state fMRI has been shown to provide surrogate biomarkers for the analysis of various diseases. In addition, fMRI data helps in understanding the brain's functional working during resting state and task-induced activity. To improve the statistical power of biomarkers and the understanding mechanism of the brain, pooling of multi-center studies has become increasingly popular. But pooling the data from multiple sites introduces variations due to hardware, software, and environment. In this paper, we look at the estimation problem of hierarchical Sparsity Connectivity Patterns (hSCPs) in fMRI data acquired on multiple sites. We introduce a simple yet effective matrix factorization based formulation to reduce site-related effects while preserving biologically relevant variations. We leverage adversarial learning in the unsupervised regime to improve the reproducibility of the components. Experiments on simulated datasets display that the proposed method can estimate components with improved accuracy and reproducibility. We also demonstrate the improved reproducibility of the components while preserving age-related variation on a real dataset compiled from multiple sites.