Identification of multi-scale hierarchical brain functional networks using deep matrix factorization

TL;DR

This paper introduces a deep semi-nonnegative matrix factorization approach to identify hierarchical, multi-scale brain functional networks from resting state fMRI data, improving subject-specific activation prediction.

Contribution

The study presents a novel deep matrix factorization method with group sparsity regularization for hierarchical multi-scale brain network detection, enhancing subject-specific analysis.

Findings

Successfully identified subject-specific multi-scale hierarchical brain networks.

Functional connectivity measures from these networks better predict individual activations.

Validated method outperforms alternative techniques in prediction accuracy.

Abstract

We present a deep semi-nonnegative matrix factorization method for identifying subject-specific functional networks (FNs) at multiple spatial scales with a hierarchical organization from resting state fMRI data. Our method is built upon a deep semi-nonnegative matrix factorization framework to jointly detect the FNs at multiple scales with a hierarchical organization, enhanced by group sparsity regularization that helps identify subject-specific FNs without loss of inter-subject comparability. The proposed method has been validated for predicting subject-specific functional activations based on functional connectivity measures of the hierarchical multi-scale FNs of the same subjects. Experimental results have demonstrated that our method could obtain subject-specific multi-scale hierarchical FNs and their functional connectivity measures across different scales could better predict subject-specific functional activations than those obtained by alternative techniques.