Functional magnetic resonance imaging for autism spectrum disorder detection using deep learning

Abstract

Autism Spectrum Disorders (ASDs) define as a scope of disability in the development of certain conditions such as social communication, imagination, and patients' capabilities to make some connection. In Malaysia, the number of ASD cases diagnosed is increasing each year. Typically, ASD patients are analyzed by doctors based on history and behavior observation without the ability to diagnose instantaneously. This research intends to study the ASD biomarker based on neuroimaging functional Magnetic Resonance Imaging (fMRI) images, which can aid doctors in diagnosing ASD. This study applies a deep learning method from Convolutional Neural Network (CNN) variants to detect either the patients are ASD or non-ASD and extract the robust characteristics from neuroimages in fMRI. Then, it interprets the performance of pre-processed images in the form of accuracy to classify the neural patterns. The Autism Brain Imaging Data Exchange (ABIDE) dataset was used to research the brain imaging of ASD patients. The results achieved using CNN models namely VGG-16 and ResNet-50 are 63.4% and 87.0% accuracy, respectively. This method also assists doctors in detecting Autism from a quantifiable method that is not dependent on the behavioral observations of suspected autistic children.