Identification of Autism Spectrum Disorder (ASD) from Medical Images using Machine Learning Algorithms

Abstract

Autism Spectrum disorder (ASD) is impairment that causes disability in socio-communal behavior. This impairment has no bio-markers and hence identification of ASD is difficult. However, if ASD could be identified at early stages, we could transform the life of person affected with ASD through appropriate trainings to improve communal behavior. Machine Learning (ML) algorithms are found to be viable tools to handle large amount of data. This paper proposes the design and development of a classifier that could classify the ASD affected subjects and normal subjects from MRI data. Experiments were conducted using ABIDE dataset and ML algorithms achieved remarkable performance in terms of accuracy when compared to results given in similar literatures.