A dynamic graph convolutional neural network framework reveals new insights into connectome dysfunctions in ADHD

• Type of Material: Article
• Authors: Kanhao Zhao, Lehigh University; Boris Duka, Lehigh University; Hua Xie, University of Maryland, College Park; Desmond J. Oathes, University of Pennsylvania; Vince D. Calhoun, Emory University; Yu Zhang, Lehigh University
• Language: English
• Date: 2021-11-30
• Publisher: Elsevier
• Publication Version: Author Accepted Manuscript (After Peer Review)
• Copyright Statement: © 2021 The Authors. Published by Elsevier Inc.
• License: Creative Commons Attribution 4.0 International
• Final Published Version (URL): https://doi.org/10.1016/j.neuroimage.2021.118774
• Title of Journal or Parent Work: NeuroImage
• Volume: 246
• Start Page: 118774
• Grant/Funding Information: This work is in part supported by Lehigh University Internal Grants (FRG, FIG, and Accelator) and Startup Funding. Portions of this research were conducted on Lehigh University’s Research Computing infrastructure partially supported by NSF Award 2019035. Dr. Oathes was funded in part by NIH RF1MH116920 and R01MH111886. Dr. Calhoun was funded in part by NIH R01MH123610.
• Keywords: Attention deficit hyperactivity disorder; Precision diagnosis; Graph convolutional networks; Brain networks; Resting-state fMRI
• Research Categories: Artificial Intelligence; Biology, Neuroscience

Abstract

The pathological mechanism of attention deficit hyperactivity disorder (ADHD) is incompletely specified, which leads to difficulty in precise diagnosis. Functional magnetic resonance imaging (fMRI) has emerged as a common neuroimaging technique for studying the brain functional connectome. Most existing methods that have either ignored or simply utilized graph structure, do not fully leverage the potentially important topological information which may be useful in characterizing brain disorders. There is a crucial need for designing nove and efficient approaches which can capture such information. To this end, we propose a new dynamic graph convolutional network (dGCN), which is trained with sparse brain regional connections from dynamically calculated graph features. We also develop a novel convolutional readout layer to improve graph representation. Our extensive experimental analysis demonstrates significantly improved performance of dGCN for ADHD diagnosis compared with existing machine learning and deep learning methods. Visualizations of the salient regions of interest (ROIs) and connectivity based on informative features learned by our model show that the identified functional abnormalities mainly involve brain regions in temporal pole, gyrus rectus, and cerebellar gyri from temporal lobe, frontal lobe, and cerebellum, respectively. A positive correlation was further observed between the identified connectomic abnormalities and ADHD symptom severity. The proposed dGCN model shows great promise in providing a functional network-based precision diagnosis of ADHD and is also broadly applicable to brain connectome-based study of mental disorders.