Multi-Feature Based Network Revealing the Structural Abnormalities in Autism Spectrum Disorder

Abstract

Autism spectrum disorder (ASD) is accompanied with impaired social-emotional functioning, such as emotional regulation and recognition, communication, and related behavior. Study of the alternations of the brain networks in ASD may not only help us in understanding this disorder but also inform us the mechanisms of affective computing in the brain. Although morphological features have been used in the diagnosis of a variety of neurological and psychiatric disorders, these features did not show significant discriminative value in identifying patients with ASD, possibly due to the omission of the information related to the changes in structural similarities among cortical regions. In this study, structural images from 66 high-functioning adults with ASD and 66 matched typically-developing controls (TDC) were used to test the hypothesis of cortico-cortical relationships are abnormal in ASD. Seven morphological features of each of the 360 brain regions were extracted and elastic network was used to quantify the similarities between each target region and all other regions. The similarities were then used to construct multi-feature-based networks (MFN), which were then submitted to a support vector machine classifier to classify the individuals of the two groups. Results showed that the classifier with features of MFN significantly improved the accuracy of discriminating patients with ASD from TDCs (78.63 percent) compared to using morphological features only (< 65 percent). The combination of MFN features with morphological features and other high-level MFN properties did not further enhance the classification performance. Our findings demonstrate that the variations in cortico-cortical similarities are important in the etiology of ASD and can be used as biomarkers in the diagnostic process.