Automatic diagnosis of autism based on functional magnetic resonance imaging and elastic net

Autism spectrum disorder (ASD) refers to a syndrome of social deficits and repetitive behaviors. It remains a behaviorally defined syndrome with no reliable biomarkers. Although many studies have been devoted to detecting clinically useful biomarkers based on resting-state functional magnetic resonance imaging (rs-fMRI), they fail to take the strong group relationships in the feature selection process, thus leading to significant information loss. To address this issue, we propose an automatic method for ASD diagnosis based on elastic net with rs-fMRI data. The advantage of the elastic network method is that it does not need to make feature selection in advance, which greatly saves time and improves the efficiency of the algorithm. Experimental results on the public database ABIDE demonstrate the effectiveness and usefulness of the proposed method.