A Mutual Multi-Scale Triplet Graph Convolutional Network for Classification of Brain Disorders Using Functional or Structural Connectivity

Classification of Neuropsychiatric Disorders via Brain-Region-Selected Graph Convolutional Network

For the classification of patients with neuropsychiatric disorders based on rs-fMRI data, this paper proposed a Brain-Region-Selected graph convolutional network (BRS-GCN). In order to effectively identify the most significant biomarkers associated with disease, we designed a novel ROI pooling score function. Additionally, we also designed a comprehensive loss function, including a group-level consistency loss function for preserving the same brain regions in subjects of the same category, and an anti-consistency function for maximizing brain region preservation differences between subjects of different categories. On the basis of the ROI graph, we directly incorporate the non-imaging information of the subjects in the network training. Experimental results on two public datasets, ABIDE and ADNI, validate the superiority of the model proposed in this paper, and the qualitative results of the biomarkers demonstrate the potential application of the model in medical diagnosis and treatment of neuropsychiatric disorders.

SAGN: Sparse Adaptive Gated Graph Neural Network With Graph Regularization for Identifying Dual-View Brain Networks

Due to the absence of a gold standard for threshold selection, brain networks constructed with inappropriate thresholds risk topological degradation or contain noise connections. Therefore, graph neural networks (GNNs) exhibit weak robustness and overfitting problems when identifying brain networks. Furthermore, existing studies have predominantly focused on strongly coupled connections, neglecting substantial evidence from other intricate systems that highlight the value of weakly coupled connections. Consequently, the potential of weakly coupled brain networks remains untapped. In this study, we pioneeringly construct weakly coupled brain networks and validate their values in emotion identification tasks. Subsequently, we propose a sparse adaptive gated GNN (SAGN) that can simultaneously perceive the valuable topology of dual-view (i.e., strongly coupled and weakly coupled) brain networks. The SAGN contains a sparse adaptive global receptive field. Moreover, SAGN employs a gated mechanism with feature enhancement and adaptive noise suppression capabilities. To address the lack of inductive bias and the large capacity of SAGN, a graph regularization term built with prior topology of dual-view brain networks is introduced to enhance generalization. Besides a public dataset (SEED), we also built a custom dataset (MuSer) with 60 subjects to evaluate weakly coupled brain networks' value and validate the SAGN's performance. Experiments demonstrate that brain physiological patterns associated with different emotional states are separable and rooted in weakly coupled brain networks. In addition, SAGN exhibits excellent generalization and robustness in identifying brain networks.

Interpretable modality-specific and interactive graph convolutional network on brain functional and structural connectomes

Both brain functional connectivity (FC) and structural connectivity (SC) provide distinct neural mechanisms for cognition and neurological disease. In addition, interactions between SC and FC within distributed association regions are related to alterations in cognition or neurological diseases, considering the inherent linkage between neural function and structure. However, there is a scarcity of existing learning-based methods that leverage both modality-specific characteristics and high-order interactions between the two modalities for regression or classification. Hence, this study proposes an interpretable modality-specific and interactive graph convolutional network (MS-Inter-GCN) that incorporates modality-specific information, reflecting the unique neural mechanism for each modality, and structure-function interactions, capturing the underlying foundation provided by white-matter fiber tracts for high-level brain function. In MS-Inter-GCN, we generate modality-specific task-relevant embeddings separately from both FC and SC using a graph convolutional encoder-decoder module. Subsequently, we learn the interactive weights between corresponding regions of FC and SC, reflecting the coupling strength, by employing an interactive module on the embeddings of both modalities. A novel graph structure is constructed, which uses modality-specific task-relevant embeddings and inserts the interactive weights as edges connecting corresponding regions of two modalities, and then is used for the regression or classification task. Finally, a post-hoc explainable technology - GNNExplainer- is used to identify salient regions and connections of each modality as well as salient interactions between FC and SC associated with tasks. We apply the proposed framework to fluid cognition prediction, Parkinson's disease (PD), Alzheimer's disease (AD), and schizophrenia (SZ) classification. Experimental results demonstrate that our method outperforms the other ten state-of-the-art methods on multi-modal brain features on all tasks. The GNNExplainer identifies salient structural and functional regions and connections for fluid cognition, PD, AD, and SZ. It confirms that strong structure-function coupling within the executive and control networks, combined with weak coupling within the motor network, is associated with fluid cognition. Moreover, structure-function decoupling in specific brain regions serves as a marker for different diseases: decoupling of the prefrontal, superior parietal, and superior occipital cortices is a marker of PD; decoupling of the middle frontal and lateral parietal cortices, temporal pole, and subcortical regions is indicative of AD; and decoupling of the prefrontal, parietal, and temporal cortices, as well as the cerebellum, contributes to SZ.

Multimodal cross-scale context clusters for classification of mental disorders using functional and structural MRI

The brain is a complex system with multiple scales and hierarchies, making it challenging to identify abnormalities in individuals with mental disorders. The dynamic segregation and integration of activities across brain regions enable flexible switching between local and global information processing modes. Modeling these scale dynamics within and between brain regions can uncover hidden correlates of brain structure and function in mental disorders. Consequently, we propose a multimodal cross-scale context clusters (MCCocs) model. First, the complementary information in the multimodal image voxels of the brain is integrated and mapped to the original target space to establish a novel voxel-level brain representation. Within each region of interest (ROI), the Voxel Reducer uses a convolution operator to extract local associations among neighboring features and achieves quantitative dimensionality reduction. Among multiple ROIs, the ROI Context Cluster Block performs unsupervised clustering of whole-brain features, capturing nonlinear relationships between ROIs through bidirectional feature aggregation to simulate the effective integration of information across regions. By alternately executing the Voxel Reducer and ROI Context Cluster Block modules multiple times, our model simulates dynamic scale switching within and between ROIs. Experimental results show that MCCocs can recognize potential discriminative biomarkers and achieve state-of-the-art performance in multiple mental disorder classification tasks. The code is available at https://github.com/yangshuqigit/MCCocs.

Self-Supervised Multi-Scale Multi-Modal Graph Pool Transformer for Sellar Region Tumor Diagnosis

The sellar region tumor is a brain tumor that only exists in the brain sellar, which affects the central nervous system. The early diagnosis of the sellar region tumor subtypes helps clinicians better understand the best treatment and recovery of patients. Magnetic resonance imaging (MRI) has proven to be an effective tool for the early detection of sellar region tumors. However, the existing sellar region tumor diagnosis still remains challenging due to the small amount of dataset and data imbalance. To overcome these challenges, we propose a novel self-supervised multi-scale multi-modal graph pool Transformer (MMGPT) network that can enhance the multi-modal fusion of small and imbalanced MRI data of sellar region tumors. MMGPT can strengthen feature interaction between multi-modal images, which makes our model more robust. A contrastive learning equipped auto-encoder (CAE) via self-supervised learning (SSL) is adopted to learn more detailed information between different samples. The proposed CAE transfers the pre-trained knowledge to the downstream tasks. Finally, a hybrid loss is equipped to relieve the performance degradation caused by data imbalance. The experimental results show that the proposed method outperforms state-of-the-art methods and obtains higher accuracy and AUC in the classification of sellar region tumors.

Task-radMBNet: An Improved Task-Driven Dynamic Graph Sparsity Pattern Radiomics-Based Morphological Brain Network for Alzheimer's Disease Characterization

Background: The study of task-driven dynamic adaptive graph sparsity patterns in Alzheimer's disease (AD) analysis is of great importance, as it allows for better focus on regions and connections of interest and enhances task sensitivity. Methods: In this study, we introduced a task-driven dynamic adaptive graph sparsity model (called task-driven radiomics-based morphological brain network [Task-radMBNet]) for AD diagnosis based on radiomics-based morphological brain network (radMBN). Specifically, the Task-radMBNet was established by devising a connectivity feature-based graph convolutional network (GCN) channel (called a connectivity-GCN channel) and a radiomics feature-based GCN channel (called a radiomics-GCN channel), where the two GCN channels shared a same dynamic sparse brain network in graph convolution but worked for different aims separately. The connectivity-GCN channel dynamically learned the graph's sparse topology that best suits the target task, while the radiomics-GCN channel combined radiomics node features and dynamic topology to improve AD diagnostic accuracy. Results: The Task-radMBNet achieved superior classification accuracy of 87.8% and 86.0% in early AD diagnosis across a total of 1273 subjects within the AD Neuroimaging Initiative and European Diffusion Tensor Imaging (DTI) Study on Dementia databases. We also visualized the topology heat map and important connectivity under different network sparse settings. Conclusions: The results demonstrated significant promise in the diagnosis of neurological disorders by integrating Task-radMBNet with radMBN.

Riemannian manifold-based disentangled representation learning for multi-site functional connectivity analysis

Functional connectivity (FC), derived from resting-state functional magnetic resonance imaging (rs-fMRI), has been widely used to characterize brain abnormalities in disorders. FC is usually defined as a correlation matrix that is a symmetric positive definite (SPD) matrix lying on the Riemannian manifold. Recently, a number of learning-based methods have been proposed for FC analysis, while the geometric properties of Riemannian manifold have not yet been fully explored in previous studies. Also, most existing methods are designed to target one imaging site of fMRI data, which may result in limited training data for learning reliable and robust models. In this paper, we propose a novel Riemannian Manifold-based Disentangled Representation Learning (RM-DRL) framework which is capable of learning invariant representations from fMRI data across multiple sites for brain disorder diagnosis. In RM-DRL, we first employ an SPD-based encoder module to learn a latent unified representation of FC from different sites, which can preserve the Riemannian geometry of the SPD matrices. In latent space, a disentangled representation module is then designed to split the learned features into domain-specific and domain-invariant parts, respectively. Finally, a decoder module is introduced to ensure that sufficient information can be preserved during disentanglement learning. These designs allow us to introduce four types of training objectives to improve the disentanglement learning. Our RM-DRL method is evaluated on the public multi-site ABIDE dataset, showing superior performance compared with several state-of-the-art methods.

Toward Integrating Federated Learning With Split Learning via Spatio-Temporal Graph Framework for Brain Disease Prediction

Functional Magnetic Resonance Imaging (fMRI) is used for extracting blood oxygen signals from brain regions to map brain functional connectivity for brain disease prediction. Despite its effectiveness, fMRI has not been widely used: on the one hand, collecting and labeling the data is time-consuming and costly, which limits the amount of valid data collected at a single healthcare site; on the other hand, integrating data from multiple sites is challenging due to data privacy restrictions. To address these issues, we propose a novel, integrated Federated learning and Split learning Spatio-temporal Graph framework (F G). Specifically, we introduce federated learning and split learning techniques to split a spatio-temporal model into a client temporal model and a server spatial model. In the client temporal model, we propose a time-aware mechanism to focus on changes in brain functional states and use an InceptionTime model to extract information about changes in the brain states of each subject. In the server spatial model, we propose a united graph convolutional network to integrate multiple graph convolutional networks. Integrating federated learning and split learning, F G can utilize multi-site fMRI data without violating data privacy protection and reduce the risk of overfitting as it is capable of learning from limited training data sets. Moreover, it boosts the extraction of spatio-temporal features of fMRI using spatio-temporal graph networks. Experiments on ABIDE and ADHD200 datasets demonstrate that our proposed method outperforms state-of-the-art methods. In addition, we explore biomarkers associated with brain disease prediction using community discovery algorithms using intermediate results of F G. The source code is available at https://github.com/yutian0315/FS2G.

Using dynamic graph convolutional network to identify individuals with major depression disorder

Objective and quantitative neuroimaging biomarkers are crucial for early diagnosis of major depressive disorder (MDD). However, previous studies using machine learning (ML) to distinguish MDD have often used small sample sizes and overlooked MDD's neural connectome and mechanism. To address these gaps, we applied Dynamic Graph Convolutional Nets (DGCNs) to a large multi-site dataset of 2317 resting state functional MRI (RS-fMRI) scans from 1081 MDD patients and 1236 healthy controls from 16 Rest-meta-MDD consortium sites. Our DGCN model combined with the personal whole brain functional connectivity (FC) network achieved an accuracy of 82.5 % (95 % CI:81.6-83.4 %, AUC:0.869), outperforming other universal ML classifiers. The most prominent domains for classification were mainly in the default mode network, fronto-parietal and cingulo-opercular network. Our study supports the stability and efficacy of using DGCN to characterize MDD and demonstrates its potential in enhancing neurobiological comprehension of MDD by detecting clinically related disorders in FC network topologies.

Multimodal multiview bilinear graph convolutional network for mild cognitive impairment diagnosis

Mild cognitive impairment (MCI) is a significant predictor of the early progression of Alzheimer's disease (AD) and can serve as an important indicator of disease progression. However, many existing methods focus mainly on the image when processing brain imaging data, ignoring other non-imaging data (e.g., genetic, clinical information, etc.) that may have underlying disease information. In addition, imaging data acquired from different devices may exhibit varying degrees of heterogeneity, potentially resulting in numerous noisy connections during network construction. To address these challenges, this study proposes a Multimodal Multiview Bilinear Graph Convolution (MMBGCN) framework for disease risk prediction. Firstly, grey matter (GM), white matter (WM) and cerebrospinal fluid (CSF) features are extracted from magnetic resonance imaging (MRI), and non-imaging information is combined with the features extracted from MRI to construct a multimodal shared adjacency matrix. The shared adjacency matrix is then used to construct the multiview network so that the effect of potential disease information in the non-imaging information on the model can be considered. Finally, the MRI features extracted by the multiview network are weighted to reduce noise, and then the spatial pattern is restored by bilinear convolution. The features of the recovered spatial patterns are then combined with the genetic information for disease prediction. The proposed method is tested on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. Extensive experiments demonstrate the superior performance of the proposed framework and its ability to outperform other related algorithms. The average classification accuracy in the binary classification task in this study is 89.6%. The experimental results demonstrate that the method proposed in this study facilitates research on MCI diagnosis using multimodal data.

Exploring Schizophrenia Classification Through Multimodal MRI and Deep Graph Neural Networks: Unveiling Brain Region-Specific Weight Discrepancies and Their Association With Cell-Type Specific Transcriptomic Features

BACKGROUND AND HYPOTHESIS

Schizophrenia (SZ) is a prevalent mental disorder that imposes significant health burdens. Diagnostic accuracy remains challenging due to clinical subjectivity. To address this issue, we explore magnetic resonance imaging (MRI) as a tool to enhance SZ diagnosis and provide objective references and biomarkers. Using deep learning with graph convolution, we represent MRI data as graphs, aligning with brain structure, and improving feature extraction, and classification. Integration of multiple modalities is expected to enhance classification.

STUDY DESIGN

Our study enrolled 683 SZ patients and 606 healthy controls from 7 hospitals, collecting structural MRI and functional MRI data. Both data types were represented as graphs, processed by 2 graph attention networks, and fused for classification. Grad-CAM with graph convolution ensured interpretability, and partial least squares analyzed gene expression in brain regions.

STUDY RESULTS

Our method excelled in the classification task, achieving 83.32% accuracy, 83.41% sensitivity, and 83.20% specificity in 10-fold cross-validation, surpassing traditional methods. And our multimodal approach outperformed unimodal methods. Grad-CAM identified potential brain biomarkers consistent with gene analysis and prior research.

CONCLUSIONS

Our study demonstrates the effectiveness of deep learning with graph attention networks, surpassing previous SZ diagnostic methods. Multimodal MRI's superiority over unimodal MRI confirms our initial hypothesis. Identifying potential brain biomarkers alongside gene biomarkers holds promise for advancing objective SZ diagnosis and research in SZ.

Jointly constrained group sparse connectivity representation improves early diagnosis of Alzheimer's disease on routinely acquired T1-weighted imaging-based brain network

Background

Radiomics-based morphological brain networks (radMBN) constructed from routinely acquired structural MRI (sMRI) data have gained attention in Alzheimer's disease (AD). However, the radMBN suffers from limited characterization of AD because sMRI only characterizes anatomical changes and is not a direct measure of neuronal pathology or brain activity.

Purpose

To establish a group sparse representation of the radMBN under a joint constraint of group-level white matter fiber connectivity and individual-level sMRI regional similarity (JCGS-radMBN).

Methods

Two publicly available datasets were adopted, including 120 subjects from ADNI with both T1-weighted image (T1WI) and diffusion MRI (dMRI) for JCGS-radMBN construction, 818 subjects from ADNI and 200 subjects solely with T1WI from AIBL for validation in early AD diagnosis. Specifically, the JCGS-radMBN was conducted by jointly estimating non-zero connections among subjects, with the regularization term constrained by group-level white matter fiber connectivity and individual-level sMRI regional similarity. Then, a triplet graph convolutional network was adopted for early AD diagnosis. The discriminative brain connections were identified using a two-sample t-test, and the neurobiological interpretation was validated by correlating the discriminative brain connections with cognitive scores.

Results

The JCGS-radMBN exhibited superior classification performance over five brain network construction methods. For the typical NC vs. AD classification, the JCGS-radMBN increased by 1-30% in accuracy over the alternatives on ADNI and AIBL. The discriminative brain connections exhibited a strong connectivity to hippocampus, parahippocampal gyrus, and basal ganglia, and had significant correlation with MMSE scores.

Conclusion

The proposed JCGS-radMBN facilitated the AD characterization of brain network established on routinely acquired imaging modality of sMRI.

Supplementary Information

The online version of this article (10.1007/s13755-023-00269-0) contains supplementary material, which is available to authorized users.

A New Brain Network Construction Paradigm for Brain Disorder via Diffusion-Based Graph Contrastive Learning

Brain network analysis plays an increasingly important role in studying brain function and the exploring of disease mechanisms. However, existing brain network construction tools have some limitations, including dependency on empirical users, weak consistency in repeated experiments and time-consuming processes. In this work, a diffusion-based brain network pipeline, DGCL is designed for end-to-end construction of brain networks. Initially, the brain region-aware module (BRAM) precisely determines the spatial locations of brain regions by the diffusion process, avoiding subjective parameter selection. Subsequently, DGCL employs graph contrastive learning to optimize brain connections by eliminating individual differences in redundant connections unrelated to diseases, thereby enhancing the consistency of brain networks within the same group. Finally, the node-graph contrastive loss and classification loss jointly constrain the learning process of the model to obtain the reconstructed brain network, which is then used to analyze important brain connections. Validation on two datasets, ADNI and ABIDE, demonstrates that DGCL surpasses traditional methods and other deep learning models in predicting disease development stages. Significantly, the proposed model improves the efficiency and generalization of brain network construction. In summary, the proposed DGCL can be served as a universal brain network construction scheme, which can effectively identify important brain connections through generative paradigms and has the potential to provide disease interpretability support for neuroscience research.

Combined graph convolutional networks with a multi-connection pattern to identify tremor-dominant Parkinson's disease and Essential tremor with resting tremor

Essential tremor with resting tremor (rET) and tremor-dominant Parkinson's disease (tPD) share many similar clinical symptoms, leading to frequent misdiagnoses. Functional connectivity (FC) matrix analysis derived from resting-state functional MRI (Rs-fMRI) offers a promising approach for early diagnosis and for exploring FC network pathogenesis in rET and tPD. However, methods relying solely on a single connection pattern may overlook the complementary roles of different connectivity patterns, resulting in reduced diagnostic differentiation. Therefore, we propose a multi-pattern connection Graph Convolutional Network (MCGCN) method to integrate information from various connection modes, distinguishing between rET and healthy controls (HC), tPD and HC, and rET and tPD. We constructed FC matrices using three different connectivity modes for each subject and used these as inputs to the MCGCN model for disease classification. The classification performance of the model was evaluated for each connectivity mode. Subsequently, gradient-weighted class activation mapping (Grad-CAM) was used to identify the most discriminative brain regions. The important brain regions identified were primarily distributed within cerebellar-motor and non-motor cortical networks. Compared with single-pattern GCN, our proposed MCGCN model demonstrated superior classification accuracy, underscoring the advantages of integrating multiple connectivity modes. Specifically, the model achieved an average accuracy of 88.0% for distinguishing rET from HC, 88.8% for rET from tPD, and 89.6% for tPD from HC. Our findings indicate that combining graph convolutional networks with multi-connection patterns can not only effectively discriminate between tPD, rET, and HC but also enhance our understanding of the functional network mechanisms underlying rET and tPD.

Hierarchical Graph Convolutional Network Built by Multiscale Atlases for Brain Disorder Diagnosis Using Functional Connectivity

Functional connectivity network (FCN) data from functional magnetic resonance imaging (fMRI) is increasingly used for the diagnosis of brain disorders. However, state-of-the-art studies used to build the FCN using a single brain parcellation atlas at a certain spatial scale, which largely neglected functional interactions across different spatial scales in hierarchical manners. In this study, we propose a novel framework to perform multiscale FCN analysis for brain disorder diagnosis. We first use a set of well-defined multiscale atlases to compute multiscale FCNs. Then, we utilize biologically meaningful brain hierarchical relationships among the regions in multiscale atlases to perform nodal pooling across multiple spatial scales, namely "Atlas-guided Pooling (AP)." Accordingly, we propose a multiscale-atlases-based hierarchical graph convolutional network (MAHGCN), built on the stacked layers of graph convolution and the AP, for a comprehensive extraction of diagnostic information from multiscale FCNs. Experiments on neuroimaging data from 1792 subjects demonstrate the effectiveness of our proposed method in the diagnoses of Alzheimer's disease (AD), the prodromal stage of AD [i.e., mild cognitive impairment (MCI)], as well as autism spectrum disorder (ASD), with the accuracy of 88.9%, 78.6%, and 72.7%, respectively. All results show significant advantages of our proposed method over other competing methods. This study not only demonstrates the feasibility of brain disorder diagnosis using resting-state fMRI empowered by deep learning but also highlights that the functional interactions in the multiscale brain hierarchy are worth being explored and integrated into deep learning network architectures for a better understanding of the neuropathology of brain disorders. The codes for MAHGCN are publicly available at "https://github.com/MianxinLiu/MAHGCN-code."

CE-GAN: Community Evolutionary Generative Adversarial Network for Alzheimer's Disease Risk Prediction

In the studies of neurodegenerative diseases such as Alzheimer's Disease (AD), researchers often focus on the associations among multi-omics pathogeny based on imaging genetics data. However, current studies overlook the communities in brain networks, leading to inaccurate models of disease development. This paper explores the developmental patterns of AD from the perspective of community evolution. We first establish a mathematical model to describe functional degeneration in the brain as the community evolution driven by entropy information propagation. Next, we propose an interpretable Community Evolutionary Generative Adversarial Network (CE-GAN) to predict disease risk. In the generator of CE-GAN, community evolutionary convolutions are designed to capture the evolutionary patterns of AD. The experiments are conducted using functional magnetic resonance imaging (fMRI) data and single nucleotide polymorphism (SNP) data. CE-GAN achieves 91.67% accuracy and 91.83% area under curve (AUC) in AD risk prediction tasks, surpassing advanced methods on the same dataset. In addition, we validated the effectiveness of CE-GAN for pathogeny extraction. The source code of this work is available at https://github.com/fmri123456/CE-GAN.

s2MRI-ADNet: an interpretable deep learning framework integrating Euclidean-graph representations of Alzheimer's disease solely from structural MRI

OBJECTIVE

To establish a multi-dimensional representation solely on structural MRI (sMRI) for early diagnosis of AD.

METHODS

A total of 3377 participants' sMRI from four independent databases were retrospectively identified to construct an interpretable deep learning model that integrated multi-dimensional representations of AD solely on sMRI (called s2MRI-ADNet) by a dual-channel learning strategy of gray matter volume (GMV) from Euclidean space and the regional radiomics similarity network (R2SN) from graph space. Specifically, the GMV feature map learning channel (called GMV-Channel) was to take into consideration spatial information of both long-range spatial relations and detailed localization information, while the node feature and connectivity strength learning channel (called NFCS-Channel) was to characterize the graph-structured R2SN network by a separable learning strategy.

RESULTS

The s2MRI-ADNet achieved a superior classification accuracy of 92.1% and 91.4% under intra-database and inter-database cross-validation. The GMV-Channel and NFCS-Channel captured complementary group-discriminative brain regions, revealing a complementary interpretation of the multi-dimensional representation of brain structure in Euclidean and graph spaces respectively. Besides, the generalizable and reproducible interpretation of the multi-dimensional representation in capturing complementary group-discriminative brain regions revealed a significant correlation between the four independent databases (p < 0.05). Significant associations (p < 0.05) between attention scores and brain abnormality, between classification scores and clinical measure of cognitive ability, CSF biomarker, metabolism, and genetic risk score also provided solid neurobiological interpretation.

CONCLUSION

The s2MRI-ADNet solely on sMRI could leverage the complementary multi-dimensional representations of AD in Euclidean and graph spaces, and achieved superior performance in the early diagnosis of AD, facilitating its potential in both clinical translation and popularization.

H-Net: Heterogeneous Neural Network for Multi-Classification of Neuropsychiatric Disorders

Clinical studies have proved that both structural magnetic resonance imaging (sMRI) and functional magnetic resonance imaging (fMRI) are implicitly associated with neuropsychiatric disorders (NDs), and integrating multi-modal to the binary classification of NDs has been thoroughly explored. However, accurately classifying multiple classes of NDs remains a challenge due to the complexity of disease subclass. In our study, we develop a heterogeneous neural network (H-Net) that integrates sMRI and fMRI modes for classifying multi-class NDs. To account for the differences between the two modes, H-Net adopts a heterogeneous neural network strategy to extract information from each mode. Specifically, H-Net includes an multi-layer perceptron based (MLP-based) encoder, a graph attention network based (GAT-based) encoder, and a cross-modality transformer block. The MLP-based and GAT-based encoders extract semantic features from sMRI and features from fMRI, respectively, while the cross-modality transformer block models the attention of two types of features. In H-Net, the proposed MLP-mixer block and cross-modality alignment are powerful tools for improving the multi-classification performance of NDs. H-Net is validate on the public dataset (CNP), where H-Net achieves 90% classification accuracy in diagnosing multi-class NDs. Furthermore, we demonstrate the complementarity of the two MRI modalities in improving the identification of multi-class NDs. Both visual and statistical analyses show the differences between ND subclasses.

MCAN: Multimodal Causal Adversarial Networks for Dynamic Effective Connectivity Learning From fMRI and EEG Data

Dynamic effective connectivity (DEC) is the accumulation of effective connectivity in the time dimension, which can describe the continuous neural activities in the brain. Recently, learning DEC from functional magnetic resonance imaging (fMRI) and electroencephalography (EEG) data has attracted the attention of neuroinformatics researchers. However, the current methods fail to consider the gap between the fMRI and EEG modality, which can not precisely learn the DEC network from multimodal data. In this paper, we propose a multimodal causal adversarial network for DEC learning, named MCAN. The MCAN contains two modules: multimodal causal generator and multimodal causal discriminator. First, MCAN employs a multimodal causal generator with an attention-guided layer to produce a posterior signal and output a set of DEC networks. Then, the proposed method uses a multimodal causal discriminator to unsupervised calculate the joint gradient, which directs the update of the whole network. The experimental results on simulated data sets show that MCAN is superior to other state-of-the-art methods in learning the network structure of DEC and can effectively estimate the brain states. The experimental results on real data sets show that MCAN can better reveal abnormal patterns of brain activity and has good application potential in brain network analysis.

Enhancing Major Depressive Disorder Diagnosis With Dynamic-Static Fusion Graph Neural Networks

Major Depressive Disorder (MDD) is a debilitating, complex mental condition with unclear mechanisms hindering diagnostic progress. Research links MDD to abnormal brain connectivity using functional magnetic resonance imaging (fMRI). Yet, existing fMRI-based MDD models suffer from limitations, including neglecting dynamic network traits, lacking interpretability, and struggling with small datasets. We present DSFGNN, a novel graph neural network framework addressing these issues for improved MDD diagnosis. DSFGNN employs a graph isomorphism encoder to model static and dynamic brain networks, achieving effective fusion of temporal and spatial information through a spatiotemporal attention mechanism, thereby enhancing interpretability. Furthermore, we incorporate a causal disentangling module and orthogonal regularization module to augment the model's expressiveness. We evaluate DSFGNN on the Rest-meta-MDD dataset, yielding superior results compared to the best baseline. Besides, extensive ablation studies and interpretability analysis confirm DSFGNN's effectiveness and potential for biomarker discovery.

A novel interactive deep cascade spectral graph convolutional network with multi-relational graphs for disease prediction

Graph neural networks (GNNs) have recently grown in popularity for disease prediction. Existing GNN-based methods primarily build the graph topological structure around a single modality and combine it with other modalities to acquire feature representations of acquisitions. The complicated relationship in each modality, however, may not be well highlighted due to its specificity. Further, relatively shallow networks restrict adequate extraction of high-level features, affecting disease prediction performance. Accordingly, this paper develops a new interactive deep cascade spectral graph convolutional network with multi-relational graphs (IDCGN) for disease prediction tasks. Its crucial points lie in constructing multiple relational graphs and dual cascade spectral graph convolution branches with interaction (DCSGBI). Specifically, the former designs a pairwise imaging-based edge generator and a pairwise non-imaging-based edge generator from different modalities by devising two learnable networks, which adaptively capture graph structures and provide various views of the same acquisition to aid in disease diagnosis. Again, DCSGBI is established to enrich high-level semantic information and low-level details of disease data. It devises a cascade spectral graph convolution operator for each branch and incorporates the interaction strategy between different branches into the network, successfully forming a deep model and capturing complementary information from diverse branches. In this manner, more favorable and sufficient features are learned for a reliable diagnosis. Experiments on several disease datasets reveal that IDCGN exceeds state-of-the-art models and achieves promising results.

Randomizing Human Brain Function Representation for Brain Disease Diagnosis

Resting-state fMRI (rs-fMRI) is an effective tool for quantifying functional connectivity (FC), which plays a crucial role in exploring various brain diseases. Due to the high dimensionality of fMRI data, FC is typically computed based on the region of interest (ROI), whose parcellation relies on a pre-defined atlas. However, utilizing the brain atlas poses several challenges including 1) subjective selection bias in choosing from various brain atlases, 2) parcellation of each subject's brain with the same atlas yet disregarding individual specificity; 3) lack of interaction between brain region parcellation and downstream ROI-based FC analysis. To address these limitations, we propose a novel randomizing strategy for generating brain function representation to facilitate neural disease diagnosis. Specifically, we randomly sample brain patches, thus avoiding ROI parcellations of the brain atlas. Then, we introduce a new brain function representation framework for the sampled patches. Each patch has its function description by referring to anchor patches, as well as the position description. Furthermore, we design an adaptive-selection-assisted Transformer network to optimize and integrate the function representations of all sampled patches within each brain for neural disease diagnosis. To validate our framework, we conduct extensive evaluations on three datasets, and the experimental results establish the effectiveness and generality of our proposed method, offering a promising avenue for advancing neural disease diagnosis beyond the confines of traditional atlas-based methods. Our code is available at https://github.com/mjliu2020/RandomFR.

Gradient Matching Federated Domain Adaptation for Brain Image Classification

Federated learning has shown its unique advantages in many different tasks, including brain image analysis. It provides a new way to train deep learning models while protecting the privacy of medical image data from multiple sites. However, previous studies suggest that domain shift across different sites may influence the performance of federated models. As a solution, we propose a gradient matching federated domain adaptation (GM-FedDA) method for brain image classification, aiming to reduce domain discrepancy with the assistance of a public image dataset and train robust local federated models for target sites. It mainly includes two stages: 1) pretraining stage; we propose a one-common-source adversarial domain adaptation (OCS-ADA) strategy, i.e., adopting ADA with gradient matching loss to pretrain encoders for reducing domain shift at each target site (private data) with the assistance of a common source domain (public data) and 2) fine-tuning stage; we develop a gradient matching federated (GM-Fed) fine-tuning method for updating local federated models pretrained with the OCS-ADA strategy, i.e., pushing the optimization direction of a local federated model toward its specific local minimum by minimizing gradient matching loss between sites. Using fully connected networks as local models, we validate our method with the diagnostic classification tasks of schizophrenia and major depressive disorder based on multisite resting-state functional MRI (fMRI), respectively. Results show that the proposed GM-FedDA method outperforms other commonly used methods, suggesting the potential of our method in brain imaging analysis and other fields, which need to utilize multisite data while preserving data privacy.

Adversarial Learning Based Node-Edge Graph Attention Networks for Autism Spectrum Disorder Identification

Graph neural networks (GNNs) have received increasing interest in the medical imaging field given their powerful graph embedding ability to characterize the non-Euclidean structure of brain networks based on magnetic resonance imaging (MRI) data. However, previous studies are largely node-centralized and ignore edge features for graph classification tasks, resulting in moderate performance of graph classification accuracy. Moreover, the generalizability of GNN model is still far from satisfactory in brain disorder [e.g., autism spectrum disorder (ASD)] identification due to considerable individual differences in symptoms among patients as well as data heterogeneity among different sites. In order to address the above limitations, this study proposes a novel adversarial learning-based node-edge graph attention network (AL-NEGAT) for ASD identification based on multimodal MRI data. First, both node and edge features are modeled based on structural and functional MRI data to leverage complementary brain information and preserved in the constructed weighted adjacent matrix for individuals through the attention mechanism in the proposed NEGAT. Second, two AL methods are employed to improve the generalizability of NEGAT. Finally, a gradient-based saliency map strategy is utilized for model interpretation to identify important brain regions and connections contributing to the classification. Experimental results based on the public Autism Brain Imaging Data Exchange I (ABIDE I) data demonstrate that the proposed framework achieves a classification accuracy of 74.7% between ASD and typical developing (TD) groups based on 1007 subjects across 17 different sites and outperforms the state-of-the-art methods, indicating satisfying classification ability and generalizability of the proposed AL-NEGAT model. Our work provides a powerful tool for brain disorder identification.

Adaptive spatial-temporal neural network for ADHD identification using functional fMRI

Computer aided diagnosis methods play an important role in Attention Deficit Hyperactivity Disorder (ADHD) identification. Dynamic functional connectivity (dFC) analysis has been widely used for ADHD diagnosis based on resting-state functional magnetic resonance imaging (rs-fMRI), which can help capture abnormalities of brain activity. However, most existing dFC-based methods only focus on dependencies between two adjacent timestamps, ignoring global dynamic evolution patterns. Furthermore, the majority of these methods fail to adaptively learn dFCs. In this paper, we propose an adaptive spatial-temporal neural network (ASTNet) comprising three modules for ADHD identification based on rs-fMRI time series. Specifically, we first partition rs-fMRI time series into multiple segments using non-overlapping sliding windows. Then, adaptive functional connectivity generation (AFCG) is used to model spatial relationships among regions-of-interest (ROIs) with adaptive dFCs as input. Finally, we employ a temporal dependency mining (TDM) module which combines local and global branches to capture global temporal dependencies from the spatially-dependent pattern sequences. Experimental results on the ADHD-200 dataset demonstrate the superiority of the proposed ASTNet over competing approaches in automated ADHD classification.

Triplet-constrained deep hashing for chest X-ray image retrieval in COVID-19 assessment

Radiology images of the chest, such as computer tomography scans and X-rays, have been prominently used in computer-aided COVID-19 analysis. Learning-based radiology image retrieval has attracted increasing attention recently, which generally involves image feature extraction and finding matches in extensive image databases based on query images. Many deep hashing methods have been developed for chest radiology image search due to the high efficiency of retrieval using hash codes. However, they often overlook the complex triple associations between images; that is, images belonging to the same category tend to share similar characteristics and vice versa. To this end, we develop a triplet-constrained deep hashing (TCDH) framework for chest radiology image retrieval to facilitate automated analysis of COVID-19. The TCDH consists of two phases, including (a) feature extraction and (b) image retrieval. For feature extraction, we have introduced a triplet constraint and an image reconstruction task to enhance discriminative ability of learned features, and these features are then converted into binary hash codes to capture semantic information. Specifically, the triplet constraint is designed to pull closer samples within the same category and push apart samples from different categories. Additionally, an auxiliary image reconstruction task is employed during feature extraction to help effectively capture anatomical structures of images. For image retrieval, we utilize learned hash codes to conduct searches for medical images. Extensive experiments on 30,386 chest X-ray images demonstrate the superiority of the proposed method over several state-of-the-art approaches in automated image search. The code is now available online.

Constructing hierarchical attentive functional brain networks for early AD diagnosis

Analyzing functional brain networks (FBN) with deep learning has demonstrated great potential for brain disorder diagnosis. The conventional construction of FBN is typically conducted at a single scale with a predefined brain region atlas. However, numerous studies have identified that the structure and function of the brain are hierarchically organized in nature. This urges the need of representing FBN in a hierarchical manner for more effective analysis of the complementary diagnostic insights at different scales. To this end, this paper proposes to build hierarchical FBNs adaptively within the Transformer framework. Specifically, a sparse attention-based node-merging module is designed to work alongside the conventional network feature extraction modules in each layer. The proposed module generates coarser nodes for further FBN construction and analysis by combining fine-grained nodes. By stacking multiple such layers, a hierarchical representation of FBN can be adaptively learned in an end-to-end manner. The hierarchical structure can not only integrate the complementary information from multiscale FBN for joint analysis, but also reduce the model complexity due to decreasing node sizes. Moreover, this paper argues that the nodes defined by the existing atlases are not necessarily the optimal starting level to build FBN hierarchy and exploring finer nodes may further enrich the FBN representation. In this regard, each predefined node in an atlas is split into multiple sub-nodes, overcoming the scale limitation of the existing atlases. Extensive experiments conducted on various data sets consistently demonstrate the superior performance of the proposed method over the competing methods.

Spectral Graph Neural Network-Based Multi-Atlas Brain Network Fusion for Major Depressive Disorder Diagnosis

Major Depressive Disorder (MDD) imposes a substantial burden within the healthcare domain, impacting millions of individuals worldwide. Functional Magnetic Resonance Imaging (fMRI) has emerged as a promising tool for the objective diagnosis of MDD, enabling the investigation of functional connectivity patterns in the brain associated with this disorder. However, most existing methods focus on a single brain atlas, which limits their ability to capture the complex, multi-scale nature of functional brain networks. To address these limitations, we propose a novel multi-atlas fusion method that incorporates early and late fusion in a unified framework. Our method introduces the concept of the holistic Functional Connectivity Network (FCN), which captures both intra-atlas relationships within individual atlases and inter-regional relationships between atlases with different brain parcellation scales. This comprehensive representation enables the identification of potential disease-related patterns associated with MDD in the early stage of our framework. Moreover, by decoding the holistic FCN from various perspectives through multiple spectral Graph Convolutional Neural Networks and fusing their results with decision-level ensembles, we further improve the performance of MDD diagnosis. Our approach is easily implemented with minimal modifications to existing model structures and demonstrates a robust performance across different baseline models. Our method, evaluated on public resting-state fMRI datasets, surpasses the current multi-atlas fusion methods, enhancing the accuracy of MDD diagnosis. The proposed novel multi-atlas fusion framework provides a more reliable MDD diagnostic technique. Experimental results show our approach outperforms both single- and multi-atlas-based methods, demonstrating its effectiveness in advancing MDD diagnosis.

The Use of Generative Adversarial Network and Graph Convolution Network for Neuroimaging-Based Diagnostic Classification

Functional connectivity (FC) obtained from resting-state functional magnetic resonance imaging has been integrated with machine learning algorithms to deliver consistent and reliable brain disease classification outcomes. However, in classical learning procedures, custom-built specialized feature selection techniques are typically used to filter out uninformative features from FC patterns to generalize efficiently on the datasets. The ability of convolutional neural networks (CNN) and other deep learning models to extract informative features from data with grid structure (such as images) has led to the surge in popularity of these techniques. However, the designs of many existing CNN models still fail to exploit the relationships between entities of graph-structure data (such as networks). Therefore, graph convolution network (GCN) has been suggested as a means for uncovering the intricate structure of brain network data, which has the potential to substantially improve classification accuracy. Furthermore, overfitting in classifiers can be largely attributed to the limited number of available training samples. Recently, the generative adversarial network (GAN) has been widely used in the medical field for its generative aspect that can generate synthesis images to cope with the problems of data scarcity and patient privacy. In our previous work, GCN and GAN have been designed to investigate FC patterns to perform diagnosis tasks, and their effectiveness has been tested on the ABIDE-I dataset. In this paper, the models will be further applied to FC data derived from more public datasets (ADHD, ABIDE-II, and ADNI) and our in-house dataset (PTSD) to justify their generalization on all types of data. The results of a number of experiments show the powerful characteristic of GAN to mimic FC data to achieve high performance in disease prediction. When employing GAN for data augmentation, the diagnostic accuracy across ADHD-200, ABIDE-II, and ADNI datasets surpasses that of other machine learning models, including results achieved with BrainNetCNN. Specifically, in ADHD, the accuracy increased from 67.74% to 73.96% with GAN, in ABIDE-II from 70.36% to 77.40%, and in ADNI, reaching 52.84% and 88.56% for multiclass and binary classification, respectively. GCN also obtains decent results, with the best accuracy in ADHD datasets at 71.38% for multinomial and 75% for binary classification, respectively, and the second-best accuracy in the ABIDE-II dataset (72.28% and 75.16%, respectively). Both GAN and GCN achieved the highest accuracy for the PTSD dataset, reaching 97.76%. However, there are still some limitations that can be improved. Both methods have many opportunities for the prediction and diagnosis of diseases.

Ordinal Pattern Tree: A New Representation Method for Brain Network Analysis

Brain networks, describing the functional or structural interactions of brain with graph theory, have been widely used for brain imaging analysis. Currently, several network representation methods have been developed for describing and analyzing brain networks. However, most of these methods ignored the valuable weighted information of the edges in brain networks. In this paper, we propose a new representation method (i.e., ordinal pattern tree) for brain network analysis. Compared with the existing network representation methods, the proposed ordinal pattern tree (OPT) can not only leverage the weighted information of the edges but also express the hierarchical relationships of nodes in brain networks. On OPT, nodes are connected by ordinal edges which are constructed by using the ordinal pattern relationships of weighted edges. We represent brain networks as OPTs and further develop a new graph kernel called optimal transport (OT) based ordinal pattern tree (OT-OPT) kernel to measure the similarity between paired brain networks. In OT-OPT kernel, the OT distances are used to calculate the transport costs between the nodes on the OPTs. Based on these OT distances, we use exponential function to calculate OT-OPT kernel which is proved to be positive definite. To evaluate the effectiveness of the proposed method, we perform classification and regression experiments on ADHD-200, ABIDE and ADNI datasets. The experimental results demonstrate that our proposed method outperforms the state-of-the-art graph methods in the classification and regression tasks.

A novel spatiotemporal graph convolutional network framework for functional connectivity biomarkers identification of Alzheimer's disease

BACKGROUND

Functional connectivity (FC) biomarkers play a crucial role in the early diagnosis and mechanistic study of Alzheimer's disease (AD). However, the identification of effective FC biomarkers remains challenging. In this study, we introduce a novel approach, the spatiotemporal graph convolutional network (ST-GCN) combined with the gradient-based class activation mapping (Grad-CAM) model (STGC-GCAM), to effectively identify FC biomarkers for AD.

METHODS

This multi-center cross-racial retrospective study involved 2,272 participants, including 1,105 cognitively normal (CN) subjects, 790 mild cognitive impairment (MCI) individuals, and 377 AD patients. All participants underwent functional magnetic resonance imaging (fMRI) and T1-weighted MRI scans. In this study, firstly, we optimized the STGC-GCAM model to enhance classification accuracy. Secondly, we identified novel AD-associated biomarkers using the optimized model. Thirdly, we validated the imaging biomarkers using Kaplan-Meier analysis. Lastly, we performed correlation analysis and causal mediation analysis to confirm the physiological significance of the identified biomarkers.

RESULTS

The STGC-GCAM model demonstrated great classification performance (The average area under the curve (AUC) values for different categories were: CN vs MCI = 0.98, CN vs AD = 0.95, MCI vs AD = 0.96, stable MCI vs progressive MCI = 0.79). Notably, the model identified specific brain regions, including the sensorimotor network (SMN), visual network (VN), and default mode network (DMN), as key differentiators between patients and CN individuals. These brain regions exhibited significant associations with the severity of cognitive impairment (p < 0.05). Moreover, the topological features of important brain regions demonstrated excellent predictive capability for the conversion from MCI to AD (Hazard ratio = 3.885, p < 0.001). Additionally, our findings revealed that the topological features of these brain regions mediated the impact of amyloid beta (Aβ) deposition (bootstrapped average causal mediation effect: β = -0.01 [-0.025, 0.00], p < 0.001) and brain glucose metabolism (bootstrapped average causal mediation effect: β = -0.02 [-0.04, -0.001], p < 0.001) on cognitive status.

CONCLUSIONS

This study presents the STGC-GCAM framework, which identifies FC biomarkers using a large multi-site fMRI dataset.

Few-Shot Domain-Adaptive Anomaly Detection for Cross-Site Brain Images

Early screening is essential for effective intervention and treatment of individuals with mental disorders. Functional magnetic resonance imaging (fMRI) is a noninvasive tool for depicting neural activity and has demonstrated strong potential as a technique for identifying mental disorders. Due to the difficulty in data collection and diagnosis, imaging data from patients are rare at a single site, whereas abundant healthy control data are available from public datasets. However, joint use of these data from multiple sites for classification model training is hindered by cross-domain distribution discrepancy and diverse label spaces. Herein, we propose few-shot domain-adaptive anomaly detection (FAAD) to achieve cross-site anomaly detection of brain images based on only a few labeled samples. We introduce domain adaptation to mitigate cross-domain distribution discrepancy and jointly align the general and conditional feature distributions of imaging data across multiple sites. We utilize fMRI data of healthy subjects in the Human Connectome Project (HCP) as the source domain and fMRI images from six independent sites, including patients with mental disorders and demographically matched healthy controls, as target domains. Experiments showed the superiority of the proposed method compared with binary classification, traditional anomaly detection methods, and several recognized domain adaptation methods.

A Multi-Graph Cross-Attention-Based Region-Aware Feature Fusion Network Using Multi-Template for Brain Disorder Diagnosis

Functional connectivity (FC) networks based on resting-state functional magnetic imaging (rs-fMRI) are reliable and sensitive for brain disorder diagnosis. However, most existing methods are limited by using a single template, which may be insufficient to reveal complex brain connectivities. Furthermore, these methods usually neglect the complementary information between static and dynamic brain networks, and the functional divergence among different brain regions, leading to suboptimal diagnosis performance. To address these limitations, we propose a novel multi-graph cross-attention based region-aware feature fusion network (MGCA-RAFFNet) by using multi-template for brain disorder diagnosis. Specifically, we first employ multi-template to parcellate the brain space into different regions of interest (ROIs). Then, a multi-graph cross-attention network (MGCAN), including static and dynamic graph convolutions, is developed to explore the deep features contained in multi-template data, which can effectively analyze complex interaction patterns of brain networks for each template, and further adopt a dual-view cross-attention (DVCA) to acquire complementary information. Finally, to efficiently fuse multiple static-dynamic features, we design a region-aware feature fusion network (RAFFNet), which is beneficial to improve the feature discrimination by considering the underlying relations among static-dynamic features in different brain regions. Our proposed method is evaluated on both public ADNI-2 and ABIDE-I datasets for diagnosing mild cognitive impairment (MCI) and autism spectrum disorder (ASD). Extensive experiments demonstrate that the proposed method outperforms the state-of-the-art methods. Our source code is available at https://github.com/mylbuaa/MGCA-RAFFNet.

Deep Fusion of Multi-Template Using Spatio-Temporal Weighted Multi-Hypergraph Convolutional Networks for Brain Disease Analysis

Conventional functional connectivity network (FCN) based on resting-state fMRI (rs-fMRI) can only reflect the relationship between pairwise brain regions. Thus, the hyper-connectivity network (HCN) has been widely used to reveal high-order interactions among multiple brain regions. However, existing HCN models are essentially spatial HCN, which reflect the spatial relevance of multiple brain regions, but ignore the temporal correlation among multiple time points. Furthermore, the majority of HCN construction and learning frameworks are limited to using a single template, while the multi-template carries richer information. To address these issues, we first employ multiple templates to parcellate the rs-fMRI into different brain regions. Then, based on the multi-template data, we propose a spatio-temporal weighted HCN (STW-HCN) to capture more comprehensive high-order temporal and spatial properties of brain activity. Next, a novel deep fusion model of multi-template called spatio-temporal weighted multi-hypergraph convolutional network (STW-MHGCN) is proposed to fuse the STW-HCN of multiple templates, which extracts the deep interrelation information between different templates. Finally, we evaluate our method on the ADNI-2 and ABIDE-I datasets for mild cognitive impairment (MCI) and autism spectrum disorder (ASD) analysis. Experimental results demonstrate that the proposed method is superior to the state-of-the-art approaches in MCI and ASD classification, and the abnormal spatio-temporal hyper-edges discovered by our method have significant significance for the brain abnormalities analysis of MCI and ASD.

A Causality-Aware Graph Convolutional Network Framework for Rigidity Assessment in Parkinsonians

Rigidity is one of the common motor disorders in Parkinson's disease (PD), which lead to life quality deterioration. The widely-used rating-scale-based approach for rigidity assessment still depends on the availability of experienced neurologists and is limited by rating subjectivity. Given the recent successful applications of quantitative susceptibility mapping (QSM) in auxiliary PD diagnosis, automated assessment of PD rigidity can be essentially achieved through QSM analysis. However, a major challenge is the performance instability due to the confounding factors (e.g., noise and distribution shift) which conceal the truly-causal features. Therefore, we propose a causality-aware graph convolutional network (GCN) framework, where causal feature selection is combined with causal invariance to ensure that causality-informed model decisions are reached. Firstly, a GCN model that integrates causal feature selection is systematically constructed at three graph levels: node, structure, and representation. In this model, a causal diagram is learned to extract a subgraph with truly-causal information. Secondly, a non-causal perturbation strategy is developed along with an invariance constraint to ensure the stability of the assessment results under different distributions, and thus avoid spurious correlations caused by distribution shifts. The superiority of the proposed method is shown by extensive experiments and the clinical value is revealed by the direct relevance of selected brain regions to rigidity in PD. Besides, its extensibility is verified on other two tasks: PD bradykinesia and mental state for Alzheimer's disease. Overall, we provide a clinically-potential tool for automated and stable assessment of PD rigidity. Our source code will be available at https://github.com/SJTUBME-QianLab/Causality-Aware-Rigidity.

Adversarially Trained Persistent Homology Based Graph Convolutional Network for Disease Identification Using Brain Connectivity

Brain disease propagation is associated with characteristic alterations in the structural and functional connectivity networks of the brain. To identify disease-specific network representations, graph convolutional networks (GCNs) have been used because of their powerful graph embedding ability to characterize the non-Euclidean structure of brain networks. However, existing GCNs generally focus on learning the discriminative region of interest (ROI) features, often ignoring important topological information that enables the integration of connectome patterns of brain activity. In addition, most methods fail to consider the vulnerability of GCNs to perturbations in network properties of the brain, which considerably degrades the reliability of diagnosis results. In this study, we propose an adversarially trained persistent homology-based graph convolutional network (ATPGCN) to capture disease-specific brain connectome patterns and classify brain diseases. First, the brain functional/structural connectivity is constructed using different neuroimaging modalities. Then, we develop a novel strategy that concatenates the persistent homology features from a brain algebraic topology analysis with readout features of the global pooling layer of a GCN model to collaboratively learn the individual-level representation. Finally, we simulate the adversarial perturbations by targeting the risk ROIs from clinical prior, and incorporate them into a training loop to evaluate the robustness of the model. The experimental results on three independent datasets demonstrate that ATPGCN outperforms existing classification methods in disease identification and is robust to minor perturbations in network architecture. Our code is available at https://github.com/CYB08/ATPGCN.

Preserving specificity in federated graph learning for fMRI-based neurological disorder identification

Resting-state functional magnetic resonance imaging (rs-fMRI) offers a non-invasive approach to examining abnormal brain connectivity associated with brain disorders. Graph neural network (GNN) gains popularity in fMRI representation learning and brain disorder analysis with powerful graph representation capabilities. Training a general GNN often necessitates a large-scale dataset from multiple imaging centers/sites, but centralizing multi-site data generally faces inherent challenges related to data privacy, security, and storage burden. Federated Learning (FL) enables collaborative model training without centralized multi-site fMRI data. Unfortunately, previous FL approaches for fMRI analysis often ignore site-specificity, including demographic factors such as age, gender, and education level. To this end, we propose a specificity-aware federated graph learning (SFGL) framework for rs-fMRI analysis and automated brain disorder identification, with a server and multiple clients/sites for federated model aggregation and prediction. At each client, our model consists of a shared and a personalized branch, where parameters of the shared branch are sent to the server while those of the personalized branch remain local. This can facilitate knowledge sharing among sites and also helps preserve site specificity. In the shared branch, we employ a spatio-temporal attention graph isomorphism network to learn dynamic fMRI representations. In the personalized branch, we integrate vectorized demographic information (i.e., age, gender, and education years) and functional connectivity networks to preserve site-specific characteristics. Representations generated by the two branches are then fused for classification. Experimental results on two fMRI datasets with a total of 1218 subjects suggest that SFGL outperforms several state-of-the-art approaches.

A multi-view convolutional neural network method combining attention mechanism for diagnosing autism spectrum disorder

Autism Spectrum Disorder (ASD) is a neurodevelopmental condition whose current psychiatric diagnostic process is subjective and behavior-based. In contrast, functional magnetic resonance imaging (fMRI) can objectively measure brain activity and is useful for identifying brain disorders. However, the ASD diagnostic models employed to date have not reached satisfactory levels of accuracy. This study proposes the use of MAACNN, a method that utilizes multi-view convolutional neural networks (CNNs) in conjunction with attention mechanisms for identifying ASD in multi-scale fMRI. The proposed algorithm effectively combines unsupervised and supervised learning. In the initial stage, we employ stacked denoising autoencoders, an unsupervised learning method for feature extraction, which provides different nodes to adapt to multi-scale data. In the subsequent stage, we perform supervised learning by employing multi-view CNNs for classification and obtain the final results. Finally, multi-scale data fusion is achieved by using the attention fusion mechanism. The ABIDE dataset is used to evaluate the model we proposed., and the experimental results show that MAACNN achieves superior performance with 75.12% accuracy and 0.79 AUC on ABIDE-I, and 72.88% accuracy and 0.76 AUC on ABIDE-II. The proposed method significantly contributes to the clinical diagnosis of ASD.

Data-driven multimodal fusion: approaches and applications in psychiatric research

In the era of big data, where vast amounts of information are being generated and collected at an unprecedented rate, there is a pressing demand for innovative data-driven multi-modal fusion methods. These methods aim to integrate diverse neuroimaging perspectives to extract meaningful insights and attain a more comprehensive understanding of complex psychiatric disorders. However, analyzing each modality separately may only reveal partial insights or miss out on important correlations between different types of data. This is where data-driven multi-modal fusion techniques come into play. By combining information from multiple modalities in a synergistic manner, these methods enable us to uncover hidden patterns and relationships that would otherwise remain unnoticed. In this paper, we present an extensive overview of data-driven multimodal fusion approaches with or without prior information, with specific emphasis on canonical correlation analysis and independent component analysis. The applications of such fusion methods are wide-ranging and allow us to incorporate multiple factors such as genetics, environment, cognition, and treatment outcomes across various brain disorders. After summarizing the diverse neuropsychiatric magnetic resonance imaging fusion applications, we further discuss the emerging neuroimaging analyzing trends in big data, such as N-way multimodal fusion, deep learning approaches, and clinical translation. Overall, multimodal fusion emerges as an imperative approach providing valuable insights into the underlying neural basis of mental disorders, which can uncover subtle abnormalities or potential biomarkers that may benefit targeted treatments and personalized medical interventions.

A comprehensive survey of complex brain network representation

Recent years have shown great merits in utilizing neuroimaging data to understand brain structural and functional changes, as well as its relationship to different neurodegenerative diseases and other clinical phenotypes. Brain networks, derived from different neuroimaging modalities, have attracted increasing attention due to their potential to gain system-level insights to characterize brain dynamics and abnormalities in neurological conditions. Traditional methods aim to pre-define multiple topological features of brain networks and relate these features to different clinical measures or demographical variables. With the enormous successes in deep learning techniques, graph learning methods have played significant roles in brain network analysis. In this survey, we first provide a brief overview of neuroimaging-derived brain networks. Then, we focus on presenting a comprehensive overview of both traditional methods and state-of-the-art deep-learning methods for brain network mining. Major models, and objectives of these methods are reviewed within this paper. Finally, we discuss several promising research directions in this field.

The Combination of a Graph Neural Network Technique and Brain Imaging to Diagnose Neurological Disorders: A Review and Outlook

Neurological disorders (NDs), such as Alzheimer's disease, have been a threat to human health all over the world. It is of great importance to diagnose ND through combining artificial intelligence technology and brain imaging. A graph neural network (GNN) can model and analyze the brain, imaging from morphology, anatomical structure, function features, and other aspects, thus becoming one of the best deep learning models in the diagnosis of ND. Some researchers have investigated the application of GNN in the medical field, but the scope is broad, and its application to NDs is less frequent and not detailed enough. This review focuses on the research progress of GNNs in the diagnosis of ND. Firstly, we systematically investigated the GNN framework of ND, including graph construction, graph convolution, graph pooling, and graph prediction. Secondly, we investigated common NDs using the GNN diagnostic model in terms of data modality, number of subjects, and diagnostic accuracy. Thirdly, we discussed some research challenges and future research directions. The results of this review may be a valuable contribution to the ongoing intersection of artificial intelligence technology and brain imaging.

Dynamic weighted hypergraph convolutional network for brain functional connectome analysis

The hypergraph structure has been utilized to characterize the brain functional connectome (FC) by capturing the high order relationships among multiple brain regions of interest (ROIs) compared with a simple graph. Accordingly, hypergraph neural network (HGNN) models have emerged and provided efficient tools for hypergraph embedding learning. However, most existing HGNN models can only be applied to pre-constructed hypergraphs with a static structure during model training, which might not be a sufficient representation of the complex brain networks. In this study, we propose a dynamic weighted hypergraph convolutional network (dwHGCN) framework to consider a dynamic hypergraph with learnable hyperedge weights. Specifically, we generate hyperedges based on sparse representation and calculate the hyper similarity as node features. The hypergraph and node features are fed into a neural network model, where the hyperedge weights are updated adaptively during training. The dwHGCN facilitates the learning of brain FC features by assigning larger weights to hyperedges with higher discriminative power. The weighting strategy also improves the interpretability of the model by identifying the highly active interactions among ROIs shared by a common hyperedge. We validate the performance of the proposed model on two classification tasks with three paradigms functional magnetic resonance imaging (fMRI) data from Philadelphia Neurodevelopmental Cohort. Experimental results demonstrate the superiority of our proposed method over existing hypergraph neural networks. We believe our model can be applied to other applications in neuroimaging for its strength in representation learning and interpretation.

Graph-matching distance between individuals' functional connectomes varies with relatedness, age, and cognitive score

Functional connectomes (FCs), represented by networks or graphs that summarize coactivation patterns between pairs of brain regions, have been related at a population level to age, sex, cognitive/behavioral scores, life experience, genetics, and disease/disorders. However, quantifying FC differences between individuals also provides a rich source of information with which to map to differences in those individuals' biology, experience, genetics or behavior. In this study, graph matching is used to create a novel inter-individual FC metric, called swap distance, that quantifies the distance between pairs of individuals' partial FCs, with a smaller swap distance indicating the individuals have more similar FC. We apply graph matching to align FCs between individuals from the the Human Connectome ProjectN = 997 and find that swap distance (i) increases with increasing familial distance, (ii) increases with subjects' ages, (iii) is smaller for pairs of females compared to pairs of males, and (iv) is larger for females with lower cognitive scores compared to females with larger cognitive scores. Regions that contributed most to individuals' swap distances were in higher-order networks, that is, default-mode and fronto-parietal, that underlie executive function and memory. These higher-order networks' regions also had swap frequencies that varied monotonically with familial relatedness of the individuals in question. We posit that the proposed graph matching technique provides a novel way to study inter-subject differences in FC and enables quantification of how FC may vary with age, relatedness, sex, and behavior.

Personalized Functional Connectivity Based Spatio-Temporal Aggregated Attention Network for MCI Identification

Functional connectivity (FC) networks deri- ved from resting-state magnetic resonance image (rs-fMRI) are effective biomarkers for identifying mild cognitive impairment (MCI) patients. However, most FC identification methods simply extract features from group-averaged brain templates, and neglect inter-subject functional variations. Furthermore, the existing methods generally concentrate on spatial correlation among brain regions, resulting in the inefficient capture of the fMRI temporal features. To address these limitations, we propose a novel personalized functional connectivity based dual-branch graph neural network with spatio-temporal aggregated attention (PFC-DBGNN-STAA) for MCI identification. Specifically, a personalized functional connectivity (PFC) template is firstly constructed to align 213 functional regions across samples and generate discriminative individualized FC features. Secondly, a dual-branch graph neural network (DBGNN) is conducted by aggregating features from the individual- and group-level templates with the cross-template FC, which is beneficial to improve the feature discrimination by considering dependency between templates. Finally, a spatio-temporal aggregated attention (STAA) module is investigated to capture the spatial and dynamic relationships between functional regions, which solves the limitation of insufficient temporal information utilization. We evaluate our proposed method on 442 samples from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database, and achieve the accuracies of 90.1%, 90.3%, 83.3% for normal control (NC) vs. early MCI (EMCI), EMCI vs. late MCI (LMCI), and NC vs. EMCI vs. LMCI classification tasks, respectively, indicating that our method boosts MCI identification performance and outperforms state-of-the-art methods.

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.

Multi-Graph Attention Networks With Bilinear Convolution for Diagnosis of Schizophrenia

The explorations of brain functional connectivity (FC) network using resting-state functional magnetic resonance imaging (rs-fMRI) can provide crucial insights into discriminative analysis of neuropsychiatric disorders such as schizophrenia (SZ). Graph attention network (GAT), which could capture the local stationary on the network topology and aggregate the features of neighboring nodes, has advantages in learning the feature representation of brain regions. However, GAT only can obtain the node-level features that reflect local information, ignoring the spatial information within the connectivity-based features that proved to be important for SZ diagnosis. In addition, existing graph learning techniques usually rely on a single graph topology to represent neighborhood information, and only consider a single correlation measure for connectivity features. Comprehensive analysis of multiple graph topologies and multiple measures of FC can leverage their complementary information that may contribute to identifying patients. In this paper, we propose a multi-graph attention network (MGAT) with bilinear convolution (BC) neural network framework for SZ diagnosis and functional connectivity analysis. Besides multiple correlation measures to construct connectivity networks from different perspectives, we further propose two different graph construction methods to capture both the low- and high-level graph topologies, respectively. Especially, the MGAT module is developed to learn multiple node interaction features on each graph topology, and the BC module is utilized to learn the spatial connectivity features of the brain network for disease prediction. Importantly, the rationality and advantages of our proposed method can be validated by the experiments on SZ identification. Therefore, we speculate that this framework may also be potentially used as a diagnostic tool for other neuropsychiatric disorders.

Multicenter and Multichannel Pooling GCN for Early AD Diagnosis Based on Dual-Modality Fused Brain Network

For significant memory concern (SMC) and mild cognitive impairment (MCI), their classification performance is limited by confounding features, diverse imaging protocols, and limited sample size. To address the above limitations, we introduce a dual-modality fused brain connectivity network combining resting-state functional magnetic resonance imaging (fMRI) and diffusion tensor imaging (DTI), and propose three mechanisms in the current graph convolutional network (GCN) to improve classifier performance. First, we introduce a DTI-strength penalty term for constructing functional connectivity networks. Stronger structural connectivity and bigger structural strength diversity between groups provide a higher opportunity for retaining connectivity information. Second, a multi-center attention graph with each node representing a subject is proposed to consider the influence of data source, gender, acquisition equipment, and disease status of those training samples in GCN. The attention mechanism captures their different impacts on edge weights. Third, we propose a multi-channel mechanism to improve filter performance, assigning different filters to features based on feature statistics. Applying those nodes with low-quality features to perform convolution would also deteriorate filter performance. Therefore, we further propose a pooling mechanism, which introduces the disease status information of those training samples to evaluate the quality of nodes. Finally, we obtain the final classification results by inputting the multi-center attention graph into the multi-channel pooling GCN. The proposed method is tested on three datasets (i.e., an ADNI 2 dataset, an ADNI 3 dataset, and an in-house dataset). Experimental results indicate that the proposed method is effective and superior to other related algorithms, with a mean classification accuracy of 93.05% in our binary classification tasks. Our code is available at: https://github.com/Xuegang-S.

Classification of Brain Disorders in rs-fMRI via Local-to-Global Graph Neural Networks

Recently, functional brain network has been used for the classification of brain disorders, such as Autism Spectrum Disorder (ASD) and Alzheimer's disease (AD). Existing methods either ignore the non-imaging information associated with the subjects and the relationship between the subjects, or cannot identify and analyze disease-related local brain regions and biomarkers, leading to inaccurate classification results. This paper proposes a local-to-global graph neural network (LG-GNN) to address this issue. A local ROI-GNN is designed to learn feature embeddings of local brain regions and identify biomarkers, and a global Subject-GNN is then established to learn the relationship between the subjects with the embeddings generated by the local ROI-GNN and the non-imaging information. The local ROI-GNN contains a self-attention based pooling module to preserve the embeddings most important for the classification. The global Subject-GNN contains an adaptive weight aggregation block to generate the multi-scale feature embedding corresponding to each subject. The proposed LG-GNN is thoroughly validated using two public datasets for ASD and AD classification. The experimental results demonstrated that it achieves the state-of-the-art performance in terms of various evaluation metrics.

GATE: Graph CCA for Temporal Self-Supervised Learning for Label-Efficient fMRI Analysis

In this work, we focus on the challenging task, neuro-disease classification, using functional magnetic resonance imaging (fMRI). In population graph-based disease analysis, graph convolutional neural networks (GCNs) have achieved remarkable success. However, these achievements are inseparable from abundant labeled data and sensitive to spurious signals. To improve fMRI representation learning and classification under a label-efficient setting, we propose a novel and theory-driven self-supervised learning (SSL) framework on GCNs, namely Graph CCA for Temporal sElf-supervised learning on fMRI analysis (GATE). Concretely, it is demanding to design a suitable and effective SSL strategy to extract formation and robust features for fMRI. To this end, we investigate several new graph augmentation strategies from fMRI dynamic functional connectives (FC) for SSL training. Further, we leverage canonical-correlation analysis (CCA) on different temporal embeddings and present the theoretical implications. Consequently, this yields a novel two-step GCN learning procedure comprised of (i) SSL on an unlabeled fMRI population graph and (ii) fine-tuning on a small labeled fMRI dataset for a classification task. Our method is tested on two independent fMRI datasets, demonstrating superior performance on autism and dementia diagnosis. Our code is available at https://github.com/LarryUESTC/GATE.