ASD-HybridNet: A hybrid deep learning framework for detection of autism spectrum disorder

Abstract

Current diagnostic methods for autism spectrum disorder (ASD) are based on subjective behavioral assessments, which present challenges to an accurate and early diagnosis. This paper proposes a hybrid deep learning framework, ASD-HybridNet, which integrates both region of interest (ROI) time series data and functional connectivity (FC) maps derived from functional magnetic resonance imaging (fMRI) data to improve ASD detection. Experiments on the ABIDE dataset demonstrate the effectiveness of the proposed method compared to existing approaches.