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

Objective To investigate the difference in behavioral and psychological symptoms among Al-zheimer's disease(AD)patients with different severity of white matter hyperintensity(WMH). Methods A total of 37 AD patients were enrolled and were followed-up for 4 weeks. They were checked by 3.0 T MRI at baseline, including T1,T2-weighted phase and fluid-attenuated inversion recovery sequence(FLAIR phase).The image pro-fessionals analyzed the images and process data.The Fazekas scale was used for WMH rating.Assessment tools in-cluded the Neuropsychiatric Inventory(NPI)、MMSE and ADAS-cog. Results There were 14 patients in none-mild WMH group and 23 patients in moderate-severe WMH group. The age of two groups were 71.3 ± 12.5 and 78.7 ± 6.1 years old respectively(P<0.05).The comparison of NPI,MMSE and ADAS-cog assessment results be-tween two groups show that there is significance difference in NPI baseline scoring and 4-week scoring.The score in moderate-severe group w is higher than that in the none-mild group(P < 0.05). However,the changed value of baseline-4-week NPI is not statistically significant. There is no significant difference between MMSE and ADAS -cog score and changed value.Conclusion Taken together,the severity of WMH may be related to behavioral and psychological symptoms of patients with Alzheimer's disease.