Extracting a Discriminative Structural Sub-Network for ASD Screening using the Evolutionary Algorithm

TL;DR

This paper presents a novel evolutionary algorithm-based method to identify discriminative brain sub-networks from neuroimaging data, improving autism screening accuracy to 76% and outperforming previous approaches.

Contribution

It introduces an evolutionary algorithm to extract discriminative structural sub-networks for ASD screening, enhancing accuracy over prior methods.

Findings

Achieved 76% average accuracy in ASD diagnosis.

Outperformed previous ASD screening methods.

Identified key brain sub-networks relevant to autism.

Abstract

Autism spectrum disorder (ASD) is one of the most significant neurological disorders that disrupt a person's social communication skills. The progression and development of neuroimaging technologies has made structural network construction of brain regions possible. In this paper, after finding the discriminative sub-network using the evolutionary algorithm, the simple features of the sub-network lead us to diagnose autism in various subjects with plausible accuracy (76% on average). This method yields substantially better results compared to previous researches. Thus, this method may be used as an accurate assistance in autism screening