Brain imaging-based machine learning in autism spectrum disorder: methods and applications

• Type of Material: Article
• Authors: Ming Xu, Institute of Automation Chinese Academy of Sciences; Vince Calhoun, Emory University; Rongtao Jiang, Institute of Automation Chinese Academy of Sciences; Weizheng Yan, Georgia State University; Jing Sui, Beijing Normal University
• Language: English
• Date: 2021-09-01
• Publisher: Elsevier B.V.
• Publication Version: Author Accepted Manuscript (After Peer Review)
• Copyright Statement: © 2021 Elsevier B.V. All rights reserved.
• License: Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International
• Final Published Version (URL): http://dx.doi.org/10.1016/j.jneumeth.2021.109271
• Title of Journal or Parent Work: Journal of Neuroscience Methods
• Volume: 361
• Start Page: 109271
• End Page: 109271
• Grant/Funding Information: This work is supported in part by the National Natural Science Foundation of China (No. 82022035, 61773380), Beijing Municipal Science and Technology Commission (Z181100001518005), China; the National Institute of Health (1R01MH117107, R01EB005846, and P20GM103472), USA.
• Keywords: Classification; Machine learning; fMRI; Prediction; Brain; Autism Spectrum Disorder; Magnetic Resonance Imaging; Neuroimaging; sMRI; Autism spectrum disorder (ASD); Child, Preschool; Machine Learning; dMRI; Humans

Abstract

Autism spectrum disorder (ASD) is a neurodevelopmental condition with early childhood onset and high heterogeneity. As the pathogenesis is still elusive, ASD diagnosis is comprised of a constellation of behavioral symptoms. Non-invasive brain imaging techniques, such as magnetic resonance imaging (MRI), provide a valuable objective measurement of the brain. Many efforts have been devoted to developing imaging-based diagnostic tools for ASD based on machine learning (ML) technologies. In this survey, we review recent advances that utilize machine learning approaches to classify individuals with and without ASD. First, we provide a brief overview of neuroimaging-based ASD classification studies, including the analysis of publications and general classification pipeline. Next, representative studies are highlighted and discussed in detail regarding different imaging modalities, methods and sample sizes. Finally, we highlight several common challenges and provide recommendations on future directions. In summary, identifying discriminative biomarkers for ASD diagnosis is challenging, and further establishing more comprehensive datasets and dissecting the individual and group heterogeneity will be critical to achieve better ADS diagnosis performance. Machine learning methods will continue to be developed and are poised to help advance the field in this regard.