Dense attentive GAN-based one-class model for detection of autism and ADHD

We investigate two neuro-developmental disorders in children- Autism Spectrum Disorder (ASD) and Attention-deficit/hyperactivity disorder (ADHD). Most works in literature have examined these disorders separately, e.g., ASD or ADHD subjects vs healthy subjects. We base our framework on the approach adopted by a paediatrician. We propose a one-class model for characterizing healthy subjects. Any subject with ASD/ADHD is considered an outlier by this one-class model. We adopt a Dense GAN architecture with self-attention modules as our one-class model. Our system uses T1-weighted longitudinal structural magnetic resonance images (sMRI) as input modalities. Further, we train our framework using longitudinal data (two scans per subject over time) only, instead of the traditional approaches using crosssectional data (one scan per subject). Our approach is similar to paediatricians diagnosing the subject over multiple sessions to confirm the disorder. Comprehensive experiments show that our proposed approach performs better than competing ASD and ADHD works.

Automated summary

This study investigates Autism Spectrum Disorder (ASD) and Attention-deficit/hyperactivity disorder (ADHD), two neuro-developmental disorders in children. The researchers propose a framework based on a pediatrician's approach and develop a one-class model for characterizing healthy subjects. Using a Dense GAN architecture with self-attention modules, they train their framework using longitudinal data to better diagnose ASD and ADHD compared to existing methods.