Graph embeddings of dynamic functional connectivity reveal discriminative patterns of task engagement in HCP data

TL;DR

This paper uses graph embedding techniques to analyze dynamic functional connectivity networks from fMRI data during working memory tasks, revealing patterns associated with task engagement.

Contribution

It introduces a framework combining dynamic connectivity estimation with graph embedding methods for interpretable analysis of brain networks.

Findings

Embeddings effectively distinguish different task engagement states.

Graph embeddings provide interpretable representations of dynamic connectivity.

Method demonstrates potential for improved brain state classification.

Abstract

There is increasing evidence to suggest functional connectivity networks are non-stationary. This has lead to the development of novel methodologies with which to accurately estimate time-varying functional connectivity networks. Many of these methods provide unprecedented temporal granularity by estimating a functional connectivity network at each point in time; resulting in high-dimensional output which can be studied in a variety of ways. One possible method is to employ graph embedding algorithms. Such algorithms effectively map estimated networks from high-dimensional spaces down to a low dimensional vector space; thus facilitating visualization, interpretation and classification. In this work, the dynamic properties of functional connectivity are studied using working memory task data from the Human Connectome Project. A recently proposed method is employed to estimate dynamic functional connectivity networks. The results are subsequently analyzed using two graph embedding methods based on linear projections. These methods are shown to provide informative embeddings that can be directly interpreted as functional connectivity networks.