Impact Factor 2.857
2017 JCR, Clarivate Analytics 2018

Frontiers journals are at the top of citation and impact metrics

This article is part of the Research Topic

Comorbidity and Autism Spectrum Disorder

Original Research ARTICLE Provisionally accepted The full-text will be published soon. Notify me

Front. Psychiatry | doi: 10.3389/fpsyt.2019.00392

A Personalized Autism Diagnosis CAD System Using a Fusion of Structural MRI and Resting State Functional MRI Data

 Omar Dekhil1, Moahmed Ali1, Yaser Elnakib1,  Ahmed Shalaby1,  Ahmed Soliman1, Andrew Switala1, Ali Mahmoud1, Mohamed Ghazal2, Hassan Hajjdiab3,  Manuel F. Casanova4, Adel Elmaghraby1, Robert Kenton1,  Ayman S. El-Baz1* and  Gregory N. Barnes1
  • 1University of Louisville, United States
  • 2Abu Dhabi University, United Arab Emirates
  • 3Abu Dhabi National Oil (United Arab Emirates), United Arab Emirates
  • 4University of South Carolina, United States

Autism spectrum disorder is a neuro-developmental disorder that affects the social abilities of the patients. Yet, the golden standard of autism diagnosis is the autism diagnosis observation schedule (ADOS). In this study we are implementing a computer-aided diagnosis system that utilizes structural MRI (sMRI) and resting state functional MRI (fMRI) to demonstrate that both anatomical abnormalities and functional connectivity abnormalities have high prediction ability of autism. The proposed system studies how the anatomical and functional connectivity metrics provides overall diagnosis of whether the subject is autistic or not and are correlated with ADOS scores. The system provides a personalized report per each subject to show what areas are more affected by autism related impairment. Our system achieved accuracy of 75% when using fMRI data only, 79% when using sMRI data only and 81% when fusing both together. Such a system achieves an important next step towards delineating the neurocircuits responsible for the autism diagnosis and hence may provide better options for physicians in devising personalized treatment plans.

Keywords: sMRI = structural MRI, fMRI, autism, Personalized diagnosis, CAD systems, machine learning

Received: 24 Nov 2018; Accepted: 17 May 2019.

Edited by:

Hanna E. Stevens, The University of Iowa, United States

Reviewed by:

Preeti Jacob, National Institute of Mental Health and Neurosciences, India
Lin Sørensen, University of Bergen, Norway  

Copyright: © 2019 Dekhil, Ali, Elnakib, Shalaby, Soliman, Switala, Mahmoud, Ghazal, Hajjdiab, Casanova, Elmaghraby, Kenton, El-Baz and Barnes. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

* Correspondence: Dr. Ayman S. El-Baz, University of Louisville, Louisville, 40292, Kentucky, United States, aselba01@louisville.edu