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.
Highlights
Autism spectrum disorder (ASD) is a neuro-developmental disorder that has three main associated characteristics [1]: i) social functioning disorders, ii) communication impairments, and iii) restricted and repetitive behaviors (RRBs)
We aim to answer two main research questions: i) Can functional MRI (fMRI) and structural MRI (sMRI) be used for autism diagnosis in an objective way? ii) Are fMRI and sMRI features associated with autism diagnostic observation schedule (ADOS) scores? The hypothesis of this study is that combined sMRI and fMRI parameters are more likely to correlate more closely with behavior and yield high diagnostic accuracy, sensitivity, and specificity
This report extends our previous fMRI findings [61,62,63] and suggests that particular MRI parameters related to the expanded neuropil in mini-columns including foldness index, social affect (SA), and volume are more relevant to defining ASD-related neural circuits [64]
Summary
Autism spectrum disorder (ASD) is a neuro-developmental disorder that has three main associated characteristics [1]: i) social functioning disorders, ii) communication impairments, and iii) restricted and repetitive behaviors (RRBs). With regard to volumetric analysis, Courchesne et al [4] conducted a study on 60 autistic and 52 typically developed individuals (ages between 2 and 16 years) to explore the anatomical abnormalities in cerebral and cerebellar volume of autistic brains with 50% of the autistic participants being aged 5 or more years and 50% between 2 and 4 years old. This result reinforced the hypothesis that the brain volume in autistic infants was larger in size than in typically developed infants This hypothesis was supported by results in the study of Hazlett et al [5], where 51 autistic and 25 typically developed individuals (ages between 1.5 and 3 years) were examined and it was found that the cerebellar white matter volume in autistic subjects between 2 and 4 years old were larger than normal size. A voxel-based morphometry (VBM) study was conducted by Toal et al [10] to study the brain anatomy of both autistic and typically developed adults (mean age is 32 years with 9 years standard deviation), and found that the brain of the autistic individuals had significant increased gray matter involving both the frontal and temporal lobes
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have