Classification of schizophrenia patients using a graph convolutional network: A combined functional MRI and connectomics analysis

Graph Neural Networks and Multimodal DTI Features for Schizophrenia Classification: Insights from Brain Network Analysis and Gene Expression

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.

Neuroimage Analysis Methods and Artificial Intelligence Techniques for Reliable Biomarkers and Accurate Diagnosis of Schizophrenia: Achievements Made by Chinese Scholars Around the Past Decade

BACKGROUND AND HYPOTHESIS

Schizophrenia (SZ) is characterized by significant cognitive and behavioral disruptions. Neuroimaging techniques, particularly magnetic resonance imaging (MRI), have been widely utilized to investigate biomarkers of SZ, distinguish SZ from healthy conditions or other mental disorders, and explore biotypes within SZ or across SZ and other mental disorders, which aim to promote the accurate diagnosis of SZ. In China, research on SZ using MRI has grown considerably in recent years.

STUDY DESIGN

The article reviews advanced neuroimaging and artificial intelligence (AI) methods using single-modal or multimodal MRI to reveal the mechanism of SZ and promote accurate diagnosis of SZ, with a particular emphasis on the achievements made by Chinese scholars around the past decade.

STUDY RESULTS

Our article focuses on the methods for capturing subtle brain functional and structural properties from the high-dimensional MRI data, the multimodal fusion and feature selection methods for obtaining important and sparse neuroimaging features, the supervised statistical analysis and classification for distinguishing disorders, and the unsupervised clustering and semi-supervised learning methods for identifying neuroimage-based biotypes. Crucially, our article highlights the characteristics of each method and underscores the interconnections among various approaches regarding biomarker extraction and neuroimage-based diagnosis, which is beneficial not only for comprehending SZ but also for exploring other mental disorders.

CONCLUSIONS

We offer a valuable review of advanced neuroimage analysis and AI methods primarily focused on SZ research by Chinese scholars, aiming to promote the diagnosis, treatment, and prevention of SZ, as well as other mental disorders, both within China and internationally.

The brain-gut microbiota network (BGMN) is correlated with symptom severity and neurocognition in patients with schizophrenia

The association between the human brain and gut microbiota, known as the "brain-gut-microbiota axis", is involved in the neuropathological mechanisms of schizophrenia (SZ); however, its association patterns and correlations with symptom severity and neurocognition are still largely unknown. In this study, 43 SZ patients and 55 normal controls (NCs) were included, and resting-state functional magnetic resonance imaging (rs-fMRI) and gut microbiota data were acquired for each participant. First, the brain features of brain images and functional brain networks were computed from rs-fMRI data; the gut features of gut microbiota abundance and the gut microbiota network were computed from gut microbiota data. Second, we propose a novel methodology to construct an individual brain-gut microbiota network (BGMN) for each participant by combining the brain and gut features via multiple strategies. Third, discriminative models between SZ patients and NCs were built using the connectivity matrices of the BGMN as input features. Moreover, the correlations between the most discriminative features and the scores of symptom severity and neurocognition were analyzed in SZ patients. The results showed that the best discriminative model between SZ patients and NCs was achieved using the connectivity matrices of the BGMN when all the brain and gut features were integrated, with an accuracy of 0.90 and an area under the curve value of 0.97. The most discriminative features were related primarily to the genera Faecalibacterium and Collinsella, in which the genus Faecalibacterium was linked to the visual system and subcortical cortices and the genus Collinsella was linked to the default network and subcortical cortices. Furthermore, parts of the most discriminative features were significantly correlated with the scores of neurocognition in the SZ patients. The methodology for constructing individual BGMNs proposed in this study can help us reveal the associations between the brain and gut microbiota and understand the neuropathology of SZ.

MO-GCN: A multi-omics graph convolutional network for discriminative analysis of schizophrenia

The methodology of machine learning with multi-omics data has been widely adopted in the discriminative analyses of schizophrenia, but most of these studies ignored the cooperative interactions and topological attributes of multi-omics networks. In this study, we constructed three types of brain graphs (BGs), three types of gut graphs (GGs), and nine types of brain-gut combined graphs (BGCGs) for each individual. We proposed a novel methodology of multi-omics graph convolutional network (MO-GCN) with an attention mechanism to construct a classification model by integrating all BGCGs. We also identified important brain and gut features using the Topk pooling layer and analyzed their correlations with the Positive and Negative Syndrome Scale (PANSS) and MATRICS Consensus Cognitive Battery (MCCB) scores. The results showed that the novel MO-GCN model using BGCGs outperformed the GCN models using either BGs or GGs. In particular, the accuracy of the best model by 5-fold cross-validation reached 84.0 %. Interpretability analysis revealed that the top 10 important brain features were primarily from the hippocampus, olfactory, fusiform and pallidum, which were involved in the brain systems of memory, learning and emotion. The top 10 important gut features were primarily from Dorea, Ruminococcus, Subdoligranulum and Clostridium, etc. Moreover, the important brain and gut features were significantly correlated with the PANSS and MCCB scores, respectively. In conclusion, the MO-GCN can effectively improve the classification performance and provide a potential gut microbiota-brain perspective for the understanding of schizophrenia.

Optimizing graph neural network architectures for schizophrenia spectrum disorder prediction using evolutionary algorithms

BACKGROUND AND OBJECTIVE

The accurate diagnosis of schizophrenia spectrum disorder plays an important role in improving patient outcomes, enabling timely interventions, and optimizing treatment plans. Functional connectivity analysis, utilizing functional magnetic resonance imaging data, has been demonstrated to offer invaluable biomarkers conducive to clinical diagnosis. However, previous studies mainly focus on traditional machine learning methods or hand-crafted neural networks, which may not fully capture the spatial topological relationship between brain regions.

METHODS

This paper proposes an evolutionary algorithm (EA) based graph neural architecture search (GNAS) method. EA-GNAS has the ability to search for high-performance graph neural networks for schizophrenia spectrum disorder prediction. Moreover, we adopt GNNExplainer to investigate the explainability of the acquired architectures, ensuring that the model's predictions are both accurate and comprehensible.

RESULTS

The results suggest that the graph neural network model, derived using genetic algorithm search, outperforms under five-fold cross-validation, achieving a fitness of 0.1850. Relative to conventional machine learning and other deep learning approaches, the proposed method yields superior accuracy, F1 score, and AUC values of 0.8246, 0.8438, and 0.8258, respectively.

CONCLUSION

Based on a multi-site dataset from schizophrenia spectrum disorder patients, the findings reveal an enhancement over prior methods, advancing our comprehension of brain function and potentially offering a biomarker for diagnosing schizophrenia spectrum disorder.

Investigating the association between symptoms and functional activity in brain regions in schizophrenia: A cross-sectional fmri-based neuroimaging study

Schizophrenia is a persistent neurological disorder profoundly affecting cognitive, emotional, and behavioral functions, prominently characterized by delusions, hallucinations, disordered speech, and abnormal motor activity. These symptoms often present diagnostic challenges due to their overlap with other forms of psychosis. Therefore, the implementation of automated diagnostic methodologies is imperative. This research leverages Functional Magnetic Resonance Imaging (fMRI), a neuroimaging modality capable of delineating functional activations across diverse brain regions. Furthermore, the utilization of evolving machine learning techniques for fMRI data analysis has significantly progressive. Here, our study stands as a novel attempt, focusing on the comprehensive assessment of both classical and atypical symptoms of schizophrenia. We aim to uncover associated changes in brain functional activity. Our study encompasses two distinct fMRI datasets (1.5T and 3T), each comprising 34 schizophrenia patients for the 1.5T dataset and 25 schizophrenia patients for the 3T dataset, along with an equal number of healthy controls. Machine learning algorithms are applied to assess data subsets, enabling an in-depth evaluation of the current functional condition concerning symptom impact. The identified voxels contribute to determining the brain regions most influenced by each symptom, as quantified by symptom intensity. This rigorous approach has yielded various new findings while maintaining an impressive classification accuracy rate of 97 %. By elucidating variations in activation patterns across multiple brain regions in individuals with schizophrenia, this study contributes to the understanding of functional brain changes associated with the disorder. The insights gained may inform differential clinical interventions and provide a means of assessing symptom severity accurately, offering new avenues for the management of schizophrenia.

Explainability of three-dimensional convolutional neural networks for functional magnetic resonance imaging of Alzheimer's disease classification based on gradient-weighted class activation mapping

Currently, numerous studies focus on employing fMRI-based deep neural networks to diagnose neurological disorders such as Alzheimer's Disease (AD), yet only a handful have provided results regarding explainability. We address this gap by applying several prevalent explainability methods such as gradient-weighted class activation mapping (Grad-CAM) to an fMRI-based 3D-VGG16 network for AD diagnosis to improve the model's explainability. The aim is to explore the specific Region of Interest (ROI) of brain the model primarily focuses on when making predictions, as well as whether there are differences in these ROIs between AD and normal controls (NCs). First, we utilized multiple resting-state functional activity maps including ALFF, fALFF, ReHo, and VMHC to reduce the complexity of fMRI data, which differed from many studies that utilized raw fMRI data. Compared to methods utilizing raw fMRI data, this manual feature extraction approach may potentially alleviate the model's burden. Subsequently, 3D-VGG16 were employed for AD classification, where the final fully connected layers were replaced with a Global Average Pooling (GAP) layer, aimed at mitigating overfitting while preserving spatial information within the feature maps. The model achieved a maximum of 96.4% accuracy on the test set. Finally, several 3D CAM methods were employed to interpret the models. In the explainability results of the models with relatively high accuracy, the highlighted ROIs were primarily located in the precuneus and the hippocampus for AD subjects, while the models focused on the entire brain for NC. This supports current research on ROIs involved in AD. We believe that explaining deep learning models would not only provide support for existing research on brain disorders, but also offer important referential recommendations for the study of currently unknown etiologies.

EEG analysis in patients with schizophrenia based on microstate semantic modeling method

Introduction

Microstate analysis enables the characterization of quasi-stable scalp potential fields on a sub-second timescale, preserving the temporal dynamics of EEG and spatial information of scalp potential distributions. Owing to its capacity to provide comprehensive pathological insights, it has been widely applied in the investigation of schizophrenia (SCZ). Nevertheless, previous research has primarily concentrated on differences in individual microstate temporal characteristics, neglecting potential distinctions in microstate semantic sequences and not fully considering the issue of the universality of microstate templates between SCZ patients and healthy individuals.

Methods

This study introduced a microstate semantic modeling analysis method aimed at schizophrenia recognition. Firstly, microstate templates corresponding to both SCZ patients and healthy individuals were extracted from resting-state EEG data. The introduction of a dual-template strategy makes a difference in the quality of microstate sequences. Quality features of microstate sequences were then extracted from four dimensions: Correlation, Explanation, Residual, and Dispersion. Subsequently, the concept of microstate semantic features was proposed, decomposing the microstate sequence into continuous sub-sequences. Specific semantic sub-sequences were identified by comparing the time parameters of sub-sequences.

Results

The SCZ recognition test was performed on the public dataset for both the quality features and semantic features of microstate sequences, yielding an impressive accuracy of 97.2%. Furthermore, cross-subject experimental validation was conducted, demonstrating that the method proposed in this paper achieves a recognition rate of 96.4% between different subjects.

Discussion

This research offers valuable insights for the clinical diagnosis of schizophrenia. In the future, further studies will seek to augment the sample size to enhance the effectiveness and reliability of this method.

Discriminative analysis of schizophrenia patients using an integrated model combining 3D CNN with 2D CNN: A multimodal MR image and connectomics analysis

OBJECTIVE

Few studies have applied deep learning to the discriminative analysis of schizophrenia (SZ) patients using the fusional features of multimodal MRI data. Here, we proposed an integrated model combining a 3D convolutional neural network (CNN) with a 2D CNN to classify SZ patients.

METHOD

Structural MRI (sMRI) and resting-state functional MRI (rs-fMRI) data were acquired for 140 SZ patients and 205 normal controls. We computed structural connectivity (SC) from the sMRI data as well as functional connectivity (FC), amplitude of low-frequency fluctuation (ALFF), and regional homogeneity (ReHo) from the rs-fMRI data. The 3D images of T1, ReHo, and ALFF were used as the inputs for the 3D CNN model, while the SC and FC matrices were used as the inputs for the 2D CNN model. Moreover, we added squeeze and excitation blocks (SE-blocks) to each layer of the integrated model and used a support vector machine (SVM) to replace the softmax classifier.

RESULTS

The integrated model proposed in this study, using the fusional features of the T1 images, and the matrices of FC, showed the best performance. The use of the SE-blocks and SVM classifiers significantly improved the performance of the integrated model, in which the accuracy, sensitivity, specificity, area under the curve, and F1-score were 89.86%, 86.21%, 92.50%, 89.35%, and 87.72%, respectively.

CONCLUSIONS

Our findings indicated that an integrated model combining 3D CNN with 2D CNN is a promising method to improve the classification performance of SZ patients and has potential for the clinical diagnosis of psychiatric diseases.

A-GCL: Adversarial graph contrastive learning for fMRI analysis to diagnose neurodevelopmental disorders

Accurate diagnosis of neurodevelopmental disorders is a challenging task due to the time-consuming cognitive tests and potential human bias in clinics. To address this challenge, we propose a novel adversarial self-supervised graph neural network (GNN) based on graph contrastive learning, named A-GCL, for diagnosing neurodevelopmental disorders using functional magnetic resonance imaging (fMRI) data. Taking advantage of the success of GNNs in psychiatric disease diagnosis using fMRI, our proposed A-GCL model is expected to improve the performance of diagnosis and provide more robust results. A-GCL takes graphs constructed from the fMRI images as input and uses contrastive learning to extract features for classification. The graphs are constructed with 3 bands of the amplitude of low-frequency fluctuation (ALFF) as node features and Pearson's correlation coefficients (PCC) of the average fMRI time series in different brain regions as edge weights. The contrastive learning creates an edge-dropped graph from a trainable Bernoulli mask to extract features that are invariant to small variations of the graph. Experiment results on three datasets - Autism Brain Imaging Data Exchange (ABIDE) I, ABIDE II, and attention deficit hyperactivity disorder (ADHD) - with 3 atlases - AAL1, AAL3, Shen268 - demonstrate the superiority and generalizability of A-GCL compared to the other GNN-based models. Extensive ablation studies verify the robustness of the proposed approach to atlas selection and model variation. Explanatory results reveal key functional connections and brain regions associated with neurodevelopmental disorders.

Dynamic Graph Clustering Learning for Unsupervised Diabetic Retinopathy Classification

Diabetic retinopathy (DR) is a common complication of diabetes, which can lead to vision loss. Early diagnosis is crucial to prevent the progression of DR. In recent years, deep learning approaches have shown promising results in the development of an intelligent and efficient system for DR classification. However, one major drawback is the need for expert-annotated datasets, which are both time-consuming and costly. To address these challenges, this paper proposes a novel dynamic graph clustering learning (DGCL) method for unsupervised classification of DR, which innovatively deploys the Euclidean and topological features from fundus images for dynamic clustering. Firstly, a multi-structural feature fusion (MFF) module extracts features from the structure of the fundus image and captures topological relationships among multiple samples, generating a fused representation. Secondly, another consistency smoothing clustering (CSC) module combines network updates and deep clustering to ensure stability and smooth performance improvement during model convergence, optimizing the clustering process by iteratively updating the network and refining the clustering results. Lastly, dynamic memory storage is utilized to track and store important information from previous iterations, enhancing the training stability and convergence. During validation, the experimental results with public datasets demonstrated the superiority of our proposed DGCL network.

Discriminative analysis of schizophrenia patients using graph convolutional networks: A combined multimodal MRI and connectomics analysis

Introduction

Recent 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.

Methods

We 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).

Results

The 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.

Discussion

Our 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.