Schizophrenia (SZ) stands as a severe psychiatric disorder. This study applied diffusion tensor imaging (DTI) data in conjunction with graph neural networks to distinguish SZ patients from normal controls (NCs) and showcases the superior performance of a graph neural network integrating combined fractional anisotropy and fiber number brain network features, achieving an accuracy of 73.79% in distinguishing SZ patients from NCs. Beyond mere discrimination, our study delved deeper into the advantages of utilizing white matter brain network features for identifying SZ patients through interpretable model analysis and gene expression analysis. These analyses uncovered intricate interrelationships between brain imaging markers and genetic biomarkers, providing novel insights into the neuropathological basis of SZ. In summary, our findings underscore the potential of graph neural networks applied to multimodal DTI data for enhancing SZ detection through an integrated analysis of neuroimaging and genetic features.
Humans ; Schizophrenia/pathology* ; Diffusion Tensor Imaging/methods* ; Male ; Female ; Adult ; Brain/metabolism* ; Young Adult ; Middle Aged ; White Matter/pathology* ; Gene Expression ; Nerve Net/diagnostic imaging* ; Graph Neural Networks

School-age children are in a specific development stage corresponding to juvenility, when the white matter of the brain experiences ongoing maturation. Diffusion-weighted magnetic resonance imaging (DWI), especially diffusion tensor imaging (DTI), is extensively used to characterize the maturation by assessing white matter properties in vivo. In the analysis of DWI data, spatial normalization is crucial for conducting inter-subject analyses or linking the individual space with the reference space. Using tensor-based registration with an appropriate diffusion tensor template presents high accuracy regarding spatial normalization. However, there is a lack of a standardized diffusion tensor template dedicated to school-age children with ongoing brain development. Here, we established the school-age children diffusion tensor (SACT) template by optimizing tensor reorientation on high-quality DTI data from a large sample of cognitively normal participants aged 6-12 years. With an age-balanced design, the SACT template represented the entire age range well by showing high similarity to the age-specific templates. Compared with the tensor template of adults, the SACT template revealed significantly higher spatial normalization accuracy and inter-subject coherence upon evaluation of subjects in two different datasets of school-age children. A practical application regarding the age associations with the normalized DTI-derived data was conducted to further compare the SACT template and the adult template. Although similar spatial patterns were found, the SACT template showed significant effects on the distributions of the statistical results, which may be related to the performance of spatial normalization. Looking forward, the SACT template could contribute to future studies of white matter development in both healthy and clinical populations. The SACT template is publicly available now ( https://figshare.com/articles/dataset/SACT_template/14071283 ).