An Autoencoder-Based Deep Learning Classifier for Efficient Diagnosis of Autism

Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder characterized by a lack of social communication and social interaction. Autism is a mental disorder that is investigated by social and computational intelligence scientists utilizing advanced technologies such as machine learning models to enhance the ability of clinicians to provide robust diagnosis and prognosis of Autism. However, with dynamic changes in Autism behavior patterns, the quality and accuracy of these models have become a great challenge for clinical practitioners. We have applied a deep neural network learning on a large brain image dataset obtained from ABIDE (Autism Brain Imaging Data Exchange) to identify ASD patients. Our deep learning model combines both unsupervised neural network learning, Autoencoder, and supervised deep learning using Convolutional Neural Network. Our proposed algorithm outperforms individual-based classifiers measured by various validations and assessment measures.