Implementation of Machine Learning and Deep Learning Models Based on Structural MRI for Identification Autism Spectrum Disorder

Abstract

Autism spectrum disorder (ASD) is a developmental disability resulting from neurological disparities. People with ASD frequently struggle with communication and social interaction, as well as limited or repetitive interests or behaviors. People with ASD may also have unique learning, movement, and attention styles. ASD sufferers can be interpreted as 1 in every 100 individuals in the globe having ASD. Abilities and requirements of autistic individuals vary and may change over time. Some autistic individuals are able to live independently, while others have severe disabilities and require lifelong care and support. Autism frequently interferes with educational and employment opportunities. Additionally, the demands placed on families providing care and assistance can be substantial. Important determinants of the quality of life for persons with autism are the attitudes of the community and the level of support provided by local and national authorities. Autism is frequently not diagnosed until adolescence, despite the fact that autistic traits are detectable in early infancy. This study will discuss the identification of Autism Spectrum Disorders using Magnetic Resonance Imaging (MRI). MRI images of ASD patients and MRI images of patients without ASD were compared. By employing multiple machine learning and deep learning techniques, such as random forests, support vector machines, and convolutional neural networks, the random forest method achieves the utmost accuracy with 100% using confusion matrix. Therefore, this technique is able to optimally identify ASD through MRI.