Diagnosis of Autism Spectrum Disorder Using Central-Moment Features From Low- and High-Order Dynamic Resting-State Functional Connectivity Networks

• Published in: Frontiers in neuroscience Vol. 14; p. 258
• Main Authors: Zhao, Feng, Chen, Zhiyuan, Rekik, Islem, Lee, Seong-Whan, Shen, Dinggang
• Format: Journal Article
• Language: English
• Published: Switzerland Frontiers Research Foundation 28.04.2020; Frontiers Media S.A
• Subjects: Autism; autism spectrum disorder; Biomarkers; Brain mapping; Brain research; central-moment features; conventional FC network; Diagnosis; Disease; dynamic functional connectivity networks; Fingerprinting; Functional magnetic resonance imaging; Magnetic resonance imaging; Neural networks; Neuroimaging; Neurological diseases; Neuroscience; resting-state functional MRI; Time series; autism spectrum disorder; conventional FC network; central-moment features; resting-state functional MRI; dynamic functional connectivity networks
• ISSN: 1662-453X; 1662-4548; 1662-453X
• DOI: 10.3389/fnins.2020.00258

The sliding-window-based dynamic functional connectivity networks (D-FCNs) derived from resting-state functional magnetic resonance imaging (rs-fMRI) are effective methods for diagnosing various neurological diseases, including autism spectrum disorder (ASD). However, traditional D-FCNs are low-order networks based on pairwise correlation between brain regions, thus overlooking high-level interactions across multiple regions of interest (ROIs). Moreover, D-FCNs suffer from the temporal mismatching issue, i.e., subnetworks in the same temporal window do not have temporal correspondence across different subjects. To address the above problems, we first construct a novel high-order D-FCNs based on the principle of "correlation's correlation" to further explore the higher level and more complex interaction relationships among multiple ROIs. Furthermore, we propose to use a central-moment method to extract temporal-invariance properties contained in either low- or high-order D-FCNs. Finally, we design and train an ensemble classifier by fusing the features extracted from conventional FCN, low-order D-FCNs, and high-order D-FCNs for the diagnosis of ASD and normal control subjects. Our method achieved the best ASD classification accuracy (83%), and our results revealed the features extracted from different networks fingerprinting the autistic brain at different connectional levels.