Simultaneous Estimation of Low- and High-Order Functional Connectivity for Identifying Mild Cognitive Impairment.

Yueying Zhou,Lishan Qiao,Weikai Li,Limei Zhang,Dinggang Shen

doi:10.3389/fninf.2018.00003

Abstract

Functional connectivity (FC) network has been becoming an increasingly useful tool for understanding the cerebral working mechanism and mining sensitive biomarkers for neural/mental disease diagnosis. Currently, Pearson's Correlation (PC) is the simplest and most commonly used scheme in FC estimation. Despite its empirical effectiveness, PC only encodes the low-order (i.e., second-order) statistics by calculating the pairwise correlations between network nodes (brain regions), which fails to capture the high-order information involved in FC (e.g., the correlations among different edges in a network). To address this issue, we propose a novel FC estimation method based on Matrix Variate Normal Distribution (MVND), which can capture both low- and high-order correlations simultaneously with a clear mathematical interpretability. Specifically, we first generate a set of BOLD subseries by the sliding window scheme, and for each subseries we construct a temporal FC network by PC. Then, we employ the constructed FC networks as samples to estimate the final low- and high-order FC networks by maximizing the likelihood of MVND. To illustrate the effectiveness of the proposed method, we conduct experiments to identify subjects with Mild Cognitive Impairment (MCI) from Normal Controls (NCs). Experimental results show that the fusion of low- and high-order FCs can generally help to improve the final classification performance, even though the high-order FC may contain less discriminative information than its low-order counterpart. Importantly, the proposed method for simultaneous estimation of low- and high-order FCs can achieve better classification performance than the two baseline methods, i.e., the original PC method and a recent high-order FC estimation method.

Highlights

We propose a new Functional connectivity (FC) network estimation framework based on Matrix Variate Normal Distribution (MVND) that can simultaneously capture low- and high-order correlation information in data
Compared with Pearson’s Correlation (PC), the proposed method encodes the temporal information by the sliding window scheme, and integrates the information based on MVND
We argue that our result is relatively reasonable, since the low-order FC determine the main tendency of the data, while the high-order FC only capture the spread of the data and could be more noisy as well

Summary

Introduction

Functional connectivity (FC) network, calculated by resting-state functional magnetic resonance imaging (rs-fMRI) (Liu et al, 2008), has become an increasingly useful tool for understanding the working mechanism of the brain and providing informative biomarkers for diagnosing some neural/mental disorders, such as autism spectrum disorder (Wee et al, 2016b; Li et al, 2017), Simultaneous Estimation of Low- and High-Order FC major depressive disorder (Greicius et al, 2007; He et al, 2016), obsessive compulsive disorder (Admon et al, 2012), schizophrenia (Zhou et al, 2007; Ganella et al, 2016), social anxiety disorder (Liu et al, 2015a,b), Alzheimer’s disease (Zhu et al, 2015; Wang et al, 2017), and its early stage, i.e., mild cognitive impairment (MCI) (Wee et al, 2012; Yu et al, 2017).In view of its great potential, how to construct high-quality FC networks comes to a key issue. We can treat the FC network as a graph, where the nodes correspond to different brain regions or, more generally, the regions-of-interest (ROIs), while the edges correspond to the pairwise FCs between these nodes. Researchers have proposed a series of FC network modeling methods (Smith et al, 2011, 2013), among which Pearson’s Correlation (PC) is the simplest and the most popular way. It has been successfully applied in FC estimation, PC can only capture the low-order (or second-order) statistical information by calculating the pairwise correlations between the network nodes (e.g., ROIs in this paper)

Methods

Results

Conclusion