Diagnostic Classification of Autism Spectrum Disorder in the Frequency Domain Using Resting-State fMRI

Autism spectrum disorder (ASD) is a neurodevelopmental disorder with problems in social interactions, verbal and non-verbal communication, repetitive behaviors, and limited interests in a person. Considering the challenges in diagnosing ASD based on behavioral symptoms-such as subjectivity, variability among individuals, and overlap with other developmental conditions-it seems necessary to propose computer-aided diagnosis systems (CADS) for ASD. We proposed an age-dependent CADS based on functional connectivity (FC) in the frequency domain for ASD using resting-state functional magnetic resonance imaging (rs-fMRI). Also, the features and classification accuracy obtained in the frequency and time domains were compared. First, preprocessing was performed on the rs-fMRI data. Then, group-independent component analysis (GICA) was used to obtain resting state networks (RSNs). This was followed by obtaining separate components of RSNs for each individual using dual regression. Then, coherence analysis was used to extract the features of FC in the frequency domain between RSNs. To consider the role of age in the classification process, three age groups of children, adolescents, and adults were considered, and feature selection for each age group was applied separately using an embedded approach, in which all classifiers in the Waikato Environment for Knowledge Analysis (WEKA) machine learning platform were used simultaneously. Finally, classification accuracy was obtained for each age group. The proposed CADS was able to classify 95.23% in the children group, 88.1% in the adolescent group, and 92.8% in the adult group. In addition, the frequency bands whose features obtained the most distinction in each age group were identified, highlighting their potential relevance for supporting ASD diagnosis and monitoring rehabilitation.