Search

IntroductionRecent studies in human brain connectomics with multimodal magnetic resonance imaging (MRI) data have widely reported abnormalities in brain structure, function and connectivity associated with schizophrenia (SZ). However, most previous discriminative studies of SZ patients were based on MRI features of brain regions, ignoring the complex relationships within brain networks.MethodsWe applied a graph convolutional network (GCN) to discriminating SZ patients using the features of brain region and connectivity derived from a combined multimodal MRI and connectomics analysis. Structural magnetic resonance imaging (sMRI) and resting-state functional magnetic resonance imaging (rs-fMRI) data were acquired from 140 SZ patients and 205 normal controls. Eighteen types of brain graphs were constructed for each subject using 3 types of node features, 3 types of edge features, and 2 brain atlases. We investigated the performance of 18 brain graphs and used the TopK pooling layers to highlight salient brain regions (nodes in the graph).ResultsThe GCN model, which used functional connectivity as edge features and multimodal features (sMRI + fMRI) of brain regions as node features, obtained the highest average accuracy of 95.8%, and outperformed other existing classification studies in SZ patients. In the explainability analysis, we reported that the top 10 salient brain regions, predominantly distributed in the prefrontal and occipital cortices, were mainly involved in the systems of emotion and visual processing.DiscussionOur findings demonstrated that GCN with a combined multimodal MRI and connectomics analysis can effectively improve the classification of SZ at an individual level, indicating a promising direction for the diagnosis of SZ patients. The code is available at https://github.com/CXY-scut/GCN-SZ.git.

Abstract The effect of the gut microbiome on the central nervous system and its possible role in mental disorders have received increasing attention. However, knowledge about the relationship between the gut microbiome and brain structure and function is still very limited. Here, we used 16S rRNA sequencing with structural magnetic resonance imaging (sMRI) and resting-state functional (rs-fMRI) to investigate differences in fecal microbiota between 38 patients with schizophrenia (SZ) and 38 demographically matched normal controls (NCs) and explored whether such differences were associated with brain structure and function. At the genus level, we found that the relative abundance of Ruminococcus and Roseburia was significantly lower, whereas the abundance of Veillonella was significantly higher in SZ patients than in NCs. Additionally, the analysis of MRI data revealed that several brain regions showed significantly lower gray matter volume (GMV) and regional homogeneity (ReHo) but significantly higher amplitude of low-frequency fluctuation in SZ patients than in NCs. Moreover, the alpha diversity of the gut microbiota showed a strong linear relationship with the values of both GMV and ReHo. In SZ patients, the ReHo indexes in the right STC (r = − 0.35, p = 0.031, FDR corrected p = 0.039), the left cuneus (r = − 0.33, p = 0.044, FDR corrected p = 0.053) and the right MTC (r = − 0.34, p = 0.03, FDR corrected p = 0.052) were negatively correlated with the abundance of the genus Roseburia. Our results suggest that the potential role of the gut microbiome in SZ is related to alterations in brain structure and function. This study provides insights into the underlying neuropathology of SZ.

Accelerated brain aging had been widely reported in patients with schizophrenia (SZ). However, brain aging trajectories in SZ patients have not been well-documented using three-modal magnetic resonance imaging (MRI) data. In this study, 138 schizophrenia patients and 205 normal controls aged 20–60 were included and multimodal MRI data were acquired for each individual, including structural MRI, resting state-functional MRI and diffusion tensor imaging. The brain age of each participant was estimated by features extracted from multimodal MRI data using linear multiple regression. The correlation between the brain age gap and chronological age in SZ patients was best fitted by a positive quadratic curve with a peak chronological age of 47.33 years. We used the peak to divide the subjects into a youth group and a middle age group. In the normal controls, brain age matched chronological age well for both the youth and middle age groups, but this was not the case for schizophrenia patients. More importantly, schizophrenia patients exhibited increased brain age in the youth group but not in the middle age group. In this study, we aimed to investigate brain aging trajectories in SZ patients using multimodal MRI data and revealed an aberrant brain age trajectory in young schizophrenia patients, providing new insights into the pathophysiological mechanisms of schizophrenia.

Interest in the application of machine learning (ML) techniques to multimodal magnetic resonance imaging (MRI) data for the diagnosis of schizophrenia (SZ) at the individual level is growing. However, a few studies have applied the features of structural and functional brain networks derived from multimodal MRI data to the discriminative analysis of SZ patients at different clinical stages. In this study, 205 normal controls (NCs), 61 first-episode drug-naive SZ (FESZ) patients, and 79 chronic SZ (CSZ) patients were recruited. We acquired their structural MRI, diffusion tensor imaging, and resting-state functional MRI data and constructed brain networks for each participant, including the gray matter network (GMN), white matter network (WMN), and functional brain network (FBN). We then calculated 3 nodal properties for each brain network, including degree centrality, nodal efficiency, and betweenness centrality. Two classifications (SZ vs. NC and FESZ vs. CSZ) were performed using five ML algorithms. We found that the SVM classifier with the input features of the combination of nodal properties of both the GMN and FBN achieved the best performance to discriminate SZ patients from NCs [accuracy, 81.2%; area under the receiver operating characteristic curve (AUC), 85.2%; p < 0.05]. Moreover, the SVM classifier with the input features of the combination of the nodal properties of both the GMN and WMN achieved the best performance to discriminate FESZ from CSZ patients (accuracy, 86.2%; AUC, 92.3%; p < 0.05). Furthermore, the brain areas in the subcortical/cerebellum network and the frontoparietal network showed significant importance in both classifications. Together, our findings provide new insights to understand the neuropathology of SZ and further highlight the potential advantages of multimodal network properties for identifying SZ patients at different clinical stages.

Recently, machine learning techniques have been widely applied in discriminative studies of schizophrenia (SZ) patients with multimodal magnetic resonance imaging (MRI); however, the effects of brain atlases and machine learning methods remain largely unknown. In this study, we collected MRI data for 61 first-episode SZ patients (FESZ), 79 chronic SZ patients (CSZ) and 205 normal controls (NC) and calculated 4 MRI measurements, including regional gray matter volume (GMV), regional homogeneity (ReHo), amplitude of low-frequency fluctuation and degree centrality. We systematically analyzed the performance of two classifications (SZ vs NC; FESZ vs CSZ) based on the combinations of three brain atlases, five classifiers, two cross validation methods and 3 dimensionality reduction algorithms. Our results showed that the groupwise whole-brain atlas with 268 ROIs outperformed the other two brain atlases. In addition, the leave-one-out cross validation was the best cross validation method to select the best hyperparameter set, but the classification performances by different classifiers and dimensionality reduction algorithms were quite similar. Importantly, the contributions of input features to both classifications were higher with the GMV and ReHo features of brain regions in the prefrontal and temporal gyri. Furthermore, an ensemble learning method was performed to establish an integrated model, in which classification performance was improved. Taken together, these findings indicated the effects of these factors in constructing effective classifiers for psychiatric diseases and showed that the integrated model has the potential to improve the clinical diagnosis and treatment evaluation of SZ.