Autism spectrum disorder (ASD) is a neurodevelopmental condition with high structural and functional heterogeneity. Multimodal fusion of structural and functional magnetic resonance imaging (MRI) allows better integration of ASD features from multiple perspectives. This study aimed to uncover the potential ASD subtypes by fusing the features of brain structure and function. An unsupervised learning method, similarity network fusion (SNF), was used. Resting-state functional MRI and structural MRI from the Autism Brain Imaging Data Exchange database of 207 male children were included in this study (105 ASD
102 healthy controls (HC)). Gray matter volume (GMV) and amplitude of low-frequency fluctuation (ALFF) were utilized to represent structural and functional features separately. Structural and functional distance networks were constructed and fused by SNF. Then spectral clustering was carried out on the fused network. At last, the multivariate support vector regression analysis was used to investigate the relationship between the multimodal alterations and symptom severity of ASD subtypes. Two ASD subtypes were identified. Compared to HC, the two ASD subtypes demonstrated opposite GMV changes and distinct ALFF alterations. Furthermore, the alterations of ALFF predicted the severity of social communication impairments in ASD subtype 1. However, no significant associations were found between the multimodal alterations and symptoms in ASD subtype 2. These findings demonstrate the existence of heterogeneity with distinct structural and functional patterns in ASD and highlight the crucial role of combining multimodal features in investigating the neural mechanism underlying ASD.