Abstract/Summary

Prior neuroimaging studies have reported white matter network underconnectivity as a potential mechanism for Autism Spectrum Disorder (ASD). In this study, we examined the structural connectome of children with ASD using Edge Density Imaging (EDI); and then applied machine leaning algorithms to identify children with ASD based on tract-based connectivity metrics. Boys aged 8 to 12 years were included: 14 with ASD and 33 typically developing children (TDC). The Edge Density (ED) maps were computed from probabilistic streamline tractography applied to high angular resolution diffusion imaging (HARDI). Tract-Based Spatial Statistics (TBSS) was used for voxel-wise comparison and coregistration of ED maps in addition to conventional DTI metrics of Fractional Anisotropy (FA), Mean Diffusivity (MD), and Radial Diffusivity (RD). Tract-based average DTI/connectome metrics were calculated and used as input for different machine learning models: naïve Bayes, random forest, support vector machines (SVM), neural networks. For these models, cross-validation was performed with stratified random sampling (×1000 permutations). The average accuracy among validation samples was calculated. In voxel-wise analysis, the body and splenium of corpus callosum, bilateral superior and posterior corona radiata, and left superior longitudinal fasciculus showed significantly lower ED in children with ASD; whereas, we could not find significant difference in FA, MD, and RD maps between the two study groups. Overall, machine-learning models using tract-based ED metrics had better performance in identification of children with ASD compared to those using FA, MD, and RD. The EDI-based random forest models had greater average accuracy (75.3%), specificity (97.0%), and positive predictive value (81.5%), whereas EDI-based polynomial SVM had greater sensitivity (51.4%), and negative predictive values (77.7%). In conclusion, we found reduced density of connectome edges in the posterior white matter tracts of children with ASD; and demonstrated the feasibility of connectome-based machine-learning algorithms in identification of children with ASD.