AUTHOR=Dekhil Omar , Ali Mohamed , El-Nakieb Yaser , Shalaby Ahmed , Soliman Ahmed , Switala Andrew , Mahmoud Ali , Ghazal Mohammed , Hajjdiab Hassan , Casanova Manuel F. , Elmaghraby Adel , Keynton Robert , El-Baz Ayman , Barnes Gregory TITLE=A Personalized Autism Diagnosis CAD System Using a Fusion of Structural MRI and Resting-State Functional MRI Data JOURNAL=Frontiers in Psychiatry VOLUME=10 YEAR=2021 URL=https://www.frontiersin.org/journals/psychiatry/articles/10.3389/fpsyt.2019.00392 DOI=10.3389/fpsyt.2019.00392 ISSN=1664-0640 ABSTRACT=

Autism spectrum disorder is a neuro-developmental disorder that affects the social abilities of the patients. Yet, the gold standard of autism diagnosis is the autism diagnostic 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 provide an overall diagnosis of whether the subject is autistic or not and are correlated with ADOS scores. The system provides a personalized report per subject to show what areas are more affected by autism-related impairment. Our system achieved accuracies 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.