Diagnosis of early Alzheimer's disease based on dynamic high order networks

Topological disruption of low- and high-order functional networks in presbycusis

Prior efforts have manifested that functional connectivity (FC) network disruptions are concerned with cognitive disorder in presbycusis. The present research was designed to investigate the topological reorganization and classification performance of low-order functional connectivity (LOFC) and high-order functional connectivity (HOFC) networks in patients with presbycusis. Resting-state functional magnetic resonance imaging (Rs-fMRI) data were obtained in 60 patients with presbycusis and 50 matched healthy control subjects (HCs). LOFC and HOFC networks were then constructed, and the topological metrics obtained from the constructed networks were compared to evaluate topological differences in global, nodal network metrics, modularity and rich-club organization between patients with presbycusis and HCs. The use of HOFC profiles boosted presbycusis classification accuracy, sensitivity and specificity compared to that using LOFC profiles. The brain networks in both patients with presbycusis and HCs exhibited small-world properties within the given threshold range, and striking differences between groups in topological metrics were discovered in the constructed networks (LOFC and HOFC). NBS analysis identified a subnetwork involving 26 nodes and 23 signally altered internodal connections in patients with presbycusis in comparison to HCs in HOFC networks. This study highlighted the topological differences between LOFC and HOFC networks in patients with presbycusis, suggesting that HOFC profiles may help to further identify brain network abnormalities in presbycusis.

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.

Addiction-related brain networks identification via Graph Diffusion Reconstruction Network

Functional magnetic resonance imaging (fMRI) provides insights into complex patterns of brain functional changes, making it a valuable tool for exploring addiction-related brain connectivity. However, effectively extracting addiction-related brain connectivity from fMRI data remains challenging due to the intricate and non-linear nature of brain connections. Therefore, this paper proposed the Graph Diffusion Reconstruction Network (GDRN), a novel framework designed to capture addiction-related brain connectivity from fMRI data acquired from addicted rats. The proposed GDRN incorporates a diffusion reconstruction module that effectively maintains the unity of data distribution by reconstructing the training samples, thereby enhancing the model's ability to reconstruct nicotine addiction-related brain networks. Experimental evaluations conducted on a nicotine addiction rat dataset demonstrate that the proposed GDRN effectively explores nicotine addiction-related brain connectivity. The findings suggest that the GDRN holds promise for uncovering and understanding the complex neural mechanisms underlying addiction using fMRI data.

Shared and Specific Changes of Cortico-Striatal Functional Connectivity in Stable Mild Cognitive Impairment and Progressive Mild Cognitive Impairment

Background

Mild cognitive impairment (MCI), the prodromal stage of Alzheimer's disease, has two distinct subtypes: stable MCI (sMCI) and progressive MCI (pMCI). Early identification of the two subtypes has important clinical significance.

Objective

We aimed to compare the cortico-striatal functional connectivity (FC) differences between the two subtypes of MCI and enhance the accuracy of differential diagnosis between sMCI and pMCI.

Methods

We collected resting-state fMRI data from 31 pMCI patients, 41 sMCI patients, and 81 healthy controls. We chose six pairs of seed regions, including the ventral striatum inferior, ventral striatum superior, dorsal-caudal putamen, dorsal-rostral putamen, dorsal caudate, and ventral-rostral putamen and analyzed the differences in cortico-striatal FC among the three groups, additionally, the relationship between the altered FC within the MCI subtypes and cognitive function was examined.

Results

Compared to sMCI, the pMCI patients exhibited decreased FC between the left dorsal-rostral putamen and right middle temporal gyrus, the right dorsal caudate and right inferior temporal gyrus, and the left dorsal-rostral putamen and left superior frontal gyrus. Additionally, the altered FC between the right inferior temporal gyrus and right putamen was significantly associated with episodic memory and executive function.

Conclusions

Our study revealed common and distinct cortico-striatal FC changes in sMCIs and pMCI across different seeds; these changes were associated with cognitive function. These findings can help us understand the underlying pathophysiological mechanisms of MCI and distinguish pMCI and sMCI in the early stage potentially.

Non-invasive detection of anemia using lip mucosa images transfer learning convolutional neural networks

Anemia is defined as a drop in the number of erythrocytes or hemoglobin concentration below normal levels in healthy people. The increase in paleness of the skin might vary based on the color of the skin, although there is currently no quantifiable measurement. The pallor of the skin is best visible in locations where the cuticle is thin, such as the interior of the mouth, lips, or conjunctiva. This work focuses on anemia-related pallors and their relationship to blood count values and artificial intelligence. In this study, a deep learning approach using transfer learning and Convolutional Neural Networks (CNN) was implemented in which VGG16, Xception, MobileNet, and ResNet50 architectures, were pre-trained to predict anemia using lip mucous images. A total of 138 volunteers (100 women and 38 men) participated in the work to develop the dataset that contains two image classes: healthy and anemic. Image processing was first performed on a single frame with only the mouth area visible, data argumentation was preformed, and then CNN models were applied to classify the dataset lip images. Statistical metrics were employed to discriminate the performance of the models in terms of Accuracy, Precision, Recal, and F1 Score. Among the CNN algorithms used, Xception was found to categorize the lip images with 99.28% accuracy, providing the best results. The other CNN architectures had accuracies of 96.38% for MobileNet, 95.65% for ResNet %, and 92.39% for VGG16. Our findings show that anemia may be diagnosed using deep learning approaches from a single lip image. This data set will be enhanced in the future to allow for real-time classification.

Explainable Vision Transformer with Self-Supervised Learning to Predict Alzheimer's Disease Progression Using 18F-FDG PET

Alzheimer's disease (AD) is a progressive neurodegenerative disorder that affects millions of people worldwide. Early and accurate prediction of AD progression is crucial for early intervention and personalized treatment planning. Although AD does not yet have a reliable therapy, several medications help slow down the disease's progression. However, more study is still needed to develop reliable methods for detecting AD and its phases. In the recent past, biomarkers associated with AD have been identified using neuroimaging methods. To uncover biomarkers, deep learning techniques have quickly emerged as a crucial methodology. A functional molecular imaging technique known as fluorodeoxyglucose positron emission tomography (18F-FDG-PET) has been shown to be effective in assisting researchers in understanding the morphological and neurological alterations to the brain associated with AD. Convolutional neural networks (CNNs) have also long dominated the field of AD progression and have been the subject of substantial research, while more recent approaches like vision transformers (ViT) have not yet been fully investigated. In this paper, we present a self-supervised learning (SSL) method to automatically acquire meaningful AD characteristics using the ViT architecture by pretraining the feature extractor using the self-distillation with no labels (DINO) and extreme learning machine (ELM) as classifier models. In this work, we examined a technique for predicting mild cognitive impairment (MCI) to AD utilizing an SSL model which learns powerful representations from unlabeled 18F-FDG PET images, thus reducing the need for large-labeled datasets. In comparison to several earlier approaches, our strategy showed state-of-the-art classification performance in terms of accuracy (92.31%), specificity (90.21%), and sensitivity (95.50%). Then, to make the suggested model easier to understand, we highlighted the brain regions that significantly influence the prediction of MCI development. Our methods offer a precise and efficient strategy for predicting the transition from MCI to AD. In conclusion, this research presents a novel Explainable SSL-ViT model that can accurately predict AD progress based on 18F-FDG PET scans. SSL, attention, and ELM mechanisms are integrated into the model to make it more predictive and interpretable. Future research will enable the development of viable treatments for neurodegenerative disorders by combining brain areas contributing to projection with observed anatomical traits.

Brain disease research based on functional magnetic resonance imaging data and machine learning: a review

Brain diseases, including neurodegenerative diseases and neuropsychiatric diseases, have long plagued the lives of the affected populations and caused a huge burden on public health. Functional magnetic resonance imaging (fMRI) is an excellent neuroimaging technology for measuring brain activity, which provides new insight for clinicians to help diagnose brain diseases. In recent years, machine learning methods have displayed superior performance in diagnosing brain diseases compared to conventional methods, attracting great attention from researchers. This paper reviews the representative research of machine learning methods in brain disease diagnosis based on fMRI data in the recent three years, focusing on the most frequent four active brain disease studies, including Alzheimer's disease/mild cognitive impairment, autism spectrum disorders, schizophrenia, and Parkinson's disease. We summarize these 55 articles from multiple perspectives, including the effect of the size of subjects, extracted features, feature selection methods, classification models, validation methods, and corresponding accuracies. Finally, we analyze these articles and introduce future research directions to provide neuroimaging scientists and researchers in the interdisciplinary fields of computing and medicine with new ideas for AI-aided brain disease diagnosis.

Characterizing Topological Properties of Brain Functional Networks Using Multi-Threshold Derivative for End-Stage Renal Disease with Mild Cognitive Impairment

Patients with end-stage renal disease (ESRD) experience changes in both the structure and function of their brain networks. In the past, cognitive impairment was often classified based on connectivity features, which only reflected the characteristics of the binary brain network or weighted brain network. It exhibited limited interpretability and stability. This study aims to quantitatively characterize the topological properties of brain functional networks (BFNs) using multi-threshold derivative (MTD), and to establish a new classification framework for end-stage renal disease with mild cognitive impairment (ESRDaMCI). The dynamic BFNs (DBFNs) were constructed and binarized with multiple thresholds, and then their topological properties were extracted from each binary brain network. These properties were then quantified by calculating their derivative curves and expressing them as multi-threshold derivative (MTD) features. The classification results of MTD features were compared with several commonly used DBFN features, and the effectiveness of MTD features in the classification of ESRDaMCI was evaluated based on the classification performance test. The results indicated that the linear fusion of MTD features improved classification performance and outperformed individual MTD features. Its accuracy, sensitivity, and specificity were 85.98 ± 2.92%, 86.10 ± 4.11%, and 81.54 ± 4.27%, respectively. Finally, the feature weights of MTD were analyzed, and MTD-cc had the highest weight percentage of 28.32% in the fused features. The MTD features effectively supplemented traditional feature quantification by addressing the issue of indistinct classification differentiation. It improved the quantification of topological properties and provided more detailed features for diagnosing cognitive disorders.

BolT: Fused window transformers for fMRI time series analysis

Deep-learning models have enabled performance leaps in analysis of high-dimensional functional MRI (fMRI) data. Yet, many previous methods are suboptimally sensitive for contextual representations across diverse time scales. Here, we present BolT, a blood-oxygen-level-dependent transformer model, for analyzing multi-variate fMRI time series. BolT leverages a cascade of transformer encoders equipped with a novel fused window attention mechanism. Encoding is performed on temporally-overlapped windows within the time series to capture local representations. To integrate information temporally, cross-window attention is computed between base tokens in each window and fringe tokens from neighboring windows. To gradually transition from local to global representations, the extent of window overlap and thereby number of fringe tokens are progressively increased across the cascade. Finally, a novel cross-window regularization is employed to align high-level classification features across the time series. Comprehensive experiments on large-scale public datasets demonstrate the superior performance of BolT against state-of-the-art methods. Furthermore, explanatory analyses to identify landmark time points and regions that contribute most significantly to model decisions corroborate prominent neuroscientific findings in the literature.

Classification of major depression disorder via using minimum spanning tree of individual high-order morphological brain network

BACKGROUND

Major depressive disorder (MDD) is an overbroad and heterogeneous diagnosis with no reliable or quantifiable markers. We aim to combine machine-learning techniques with the individual minimum spanning tree of the morphological brain network (MST-MBN) to determine whether the network properties can provide neuroimaging biomarkers to identify patients with MDD.

METHOD

Eight morphometric features of each region of interest (ROI) were extracted from 3D T1 structural images of 106 patients with MDD and 97 healthy controls. Six feature distances of the eight morphometric features were calculated to generate a feature distance matrix, which was defined as low-order MBN. Further linear correlations of feature distances between ROIs were calculated on the basis of low-order MBN to generate individual high-order MBN. The Kruskal's algorithm was used to generate the MST to obtain the core framework of individual low-order and high-order MBN. The regional and global properties of the individual MSTs were defined as the feature. The support vector machine and back-propagation neural network was used to diagnose MDD and assess its severity, respectively.

RESULT

The low-order and high-order MST-MBN constructed by cityblock distance had the excellent classification performance. The high-order MST-MBN significantly improved almost 20 % diagnostic accuracy compared with the low-order MST-MBN, and had a maximum R² value of 0.939 between the predictive and true Hamilton Depression Scale score. The different group-level connectivity strength mainly involves the central executive network and default mode network (no statistical significance after FDR correction).

CONCLUSION

We proposed an innovative individual high-order MST-MBN to capture the cortical high-order morphological correlation and make an excellent performance for individualized diagnosis and assessment of MDD.

SD-CNN: A static-dynamic convolutional neural network for functional brain networks

Static functional connections (sFCs) and dynamic functional connections (dFCs) have been widely used in the resting-state functional MRI (rs-fMRI) analysis. sFCs, calculated based on entire rs-fMRI scans, can accurately describe the static topology of the brain network. dFCs, estimated by dividing rs-fMRI scans into a series of short sliding windows, are used to reveal time-varying changes in FC patterns. Currently, how to jointly use sFCs and dFCs to identify brain diseases under the framework of deep learning is still a hot issue. To this end, we propose a static-dynamic convolutional neural network for functional brain networks, which involves a static pathway and a dynamic pathway for taking full advantages of sFCs and dFCs. Specifically, the static pathway, using high-resolution convolution filters (i.e., convolution filters with a high number of channels) at a single adjacency matrix of sFCs, is performed to capture static FC patterns. The dynamic pathway, using low-resolution convolution filters at each adjacency matrix of dFCs, is performed to capture time-varying FC patterns. Two types of diffusion connections are used in this model for encouraging the transfer of information between the static pathway and the dynamic pathway, which can make the learned features more discriminative. Furthermore, a static and dynamic combination classifier is introduced to combine features from two pathways for identifying brain diseases. Experiments on two real datasets demonstrate the effectiveness and advantages of our proposed method.

Topological disruption of high-order functional networks in cognitively preserved Parkinson's disease

AIMS

This study aimed to characterize the topological alterations and classification performance of high-order functional connectivity (HOFC) networks in cognitively preserved patients with Parkinson's disease (PD), relative to low-order FC (LOFC) networks.

METHODS

The topological metrics of the constructed networks (LOFC and HOFC) obtained from fifty-one cognitively normal patients with PD and 60 matched healthy control subjects were analyzed. The discriminative abilities were evaluated using machine learning approach.

RESULTS

The HOFC networks in the PD group showed decreased segregation and integration. The normalized clustering coefficient and small-worldness in the HOFC networks were correlated to motor performance. The altered nodal centralities (distributed in the precuneus, putamen, lingual gyrus, supramarginal gyrus, motor area, postcentral gyrus and inferior occipital gyrus) and intermodular FC (frontoparietal and visual networks, sensorimotor and subcortical networks) were specific to HOFC networks. Several highly connected nodes (thalamus, paracentral lobule, calcarine fissure and precuneus) and improved classification performance were found based on HOFC profiles.

CONCLUSION

This study identified disrupted topology of functional interactions at a high level with extensive alterations in topological properties and improved differentiation ability in patients with PD prior to clinical symptoms of cognitive impairment, providing complementary insights into complex neurodegeneration in PD.

A Multi-Modal and Multi-Atlas Integrated Framework for Identification of Mild Cognitive Impairment

Background: Multi-modal neuroimaging with appropriate atlas is vital for effectively differentiating mild cognitive impairment (MCI) from healthy controls (HC). Methods: The resting-state functional magnetic resonance imaging (rs-fMRI) and structural MRI (sMRI) of 69 MCI patients and 61 HC subjects were collected. Then, the gray matter volumes obtained from the sMRI and Hurst exponent (HE) values calculated from rs-fMRI data in the Automated Anatomical Labeling (AAL-90), Brainnetome (BN-246), Harvard–Oxford (HOA-112) and AAL3-170 atlases were extracted, respectively. Next, these characteristics were selected with a minimal redundancy maximal relevance algorithm and a sequential feature collection method in single or multi-modalities, and only the optimal features were retained after this procedure. Lastly, the retained characteristics were served as the input features for the support vector machine (SVM)-based method to classify MCI patients, and the performance was estimated with a leave-one-out cross-validation (LOOCV). Results: Our proposed method obtained the best 92.00% accuracy, 94.92% specificity and 89.39% sensitivity with the sMRI in AAL-90 and the fMRI in HOA-112 atlas, which was much better than using the single-modal or single-atlas features. Conclusion: The results demonstrated that the multi-modal and multi-atlas integrated method could effectively recognize MCI patients, which could be extended into various neurological and neuropsychiatric diseases.

Temporal and Spatial Analysis of Alzheimer's Disease Based on an Improved Convolutional Neural Network and a Resting-State FMRI Brain Functional Network

Most current research on Alzheimer’s disease (AD) is based on transverse measurements. Given the nature of neurodegeneration in AD progression, observing longitudinal changes in the structural features of brain networks over time may improve the accuracy of the predicted transformation and provide a good measure of the progression of AD. Currently, there is no cure for patients with existing AD dementia, but patients with mild cognitive impairment (MCI) in the prodromal stage of AD dementia may be diagnosed. The study of the early diagnosis of MCI and the prediction of MCI to AD transformation is of great significance for the monitoring of the MCI to AD transformation process. Despite the high rate of MCI conversion to AD, the neuropathological cause of MCI is heterogeneous. However, many people with MCI remain stable. Treatment options are different for patients with stable MCI and those with underlying dementia. Therefore, it is of great significance for clinical practice to predict whether patients with MCI will develop AD dementia. This paper proposes an improved algorithm that is based on a convolution neural network (CNN) with residuals combined with multi-layer long short-term memory (LSTM) to diagnose AD and predict MCI. Firstly, multi-time resting-state fMRI images were obtained from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database for preprocessing, and then an AAL brain partition template was used to construct a 90 × 90 functional connectivity (FC) network matrix of a whole-brain region of interest (ROI). Secondly, the diversity of training samples was increased by generating an adversarial network (GAN). Finally, a CNN with residuals and a multi-layer LSTM model were constructed to automatically classify and predict the functional adjacency matrix. This method can not only distinguish Alzheimer’s disease from normal health conditions at multiple time points, but can also predict progressive MCI (pMCI) and stable MCI (sMCI) at multiple time points. The classification accuracies in AD vs. NC and sMCI vs.pMCI reached 93.5% and 75.5%, respectively.

A Spatiotemporal Brain Network Analysis of Alzheimer’s Disease Based on Persistent Homology

Current brain network studies based on persistent homology mainly focus on the spatial evolution over multiple spatial scales, and there is little research on the evolution of a spatiotemporal brain network of Alzheimer’s disease (AD). This paper proposed a persistent homology-based method by combining multiple temporal windows and spatial scales to study the spatiotemporal evolution of brain functional networks. Specifically, a time-sliding window method was performed to establish a spatiotemporal network, and the persistent homology-based features of such a network were obtained. We evaluated our proposed method using the resting-state functional MRI (rs-fMRI) data set from Alzheimer’s Disease Neuroimaging Initiative (ADNI) with 31 patients with AD and 37 normal controls (NCs). In the statistical analysis experiment, most network properties showed a better statistical power in spatiotemporal networks than in spatial networks. Moreover, compared to the standard graph theory properties in spatiotemporal networks, the persistent homology-based features detected more significant differences between the groups. In the clustering experiment, the brain networks on the sliding windows of all subjects were clustered into two highly structured connection states. Compared to the NC group, the AD group showed a longer residence time and a higher window ratio in a weak connection state, which may be because patients with AD have not established a firm connection. In summary, we constructed a spatiotemporal brain network containing more detailed information, and the dynamic spatiotemporal brain network analysis method based on persistent homology provides stronger adaptability and robustness in revealing the abnormalities of the functional organization of patients with AD.

Disrupted Dynamic Functional Connectivity in Distinguishing Subjective Cognitive Decline and Amnestic Mild Cognitive Impairment Based on the Triple-Network Model

Background: Subjective cognitive decline and amnestic mild cognitive impairment (aMCI) were widely thought to be preclinical AD spectrum disorders, characterized by aberrant functional connectivity (FC) within the triple networks of the default mode network (DMN), the salience network (SN), and the executive control network (ECN). Dynamic FC (DFC) analysis can capture temporal fluctuations in brain FC during the scan, which static FC analysis cannot. The purpose of the current study was to explore the changes in dynamic FC within the triple networks of the preclinical AD spectrum and further reveal their potential diagnostic value in diagnosing preclinical AD spectrum disorders.

Methods: We collected resting-state functional magnetic resonance imaging data from 44 patients with subjective cognitive decline (SCD), 49 with aMCI, and 58 healthy controls (HCs). DFC analysis based on the sliding time-window correlation method was used to analyze DFC variability within the triple networks in the three groups. Then, correlation analysis was conducted to reveal the relationship between altered DFC variability within the triple networks and a decline in cognitive function. Furthermore, logistic regression analysis was used to assess the diagnostic accuracy of altered DFC variability within the triple networks in patients with SCD and aMCI.

Results: Compared with the HC group, the groups with SCD and aMCI both showed altered DFC variability within the triple networks. DFC variability in the right middle temporal gyrus and left inferior frontal gyrus (IFG) within the ECN were significantly different between patients with SCD and aMCI. Moreover, the altered DFC variability in the left IFG within the ECN was obviously associated with a decline in episodic memory and executive function. The logistic regression analysis showed that multivariable analysis had high sensitivity and specificity for diagnosing SCD and aMCI.

Conclusions: Subjective cognitive decline and aMCI showed varying degrees of change in DFC variability within the triple networks and altered DFC variability within the ECN involved episodic memory and executive function. More importantly, altered DFC variability and the triple-network model proved to be important biomarkers for diagnosing and identifying patients with preclinical AD spectrum disorders.

Convolutional Neural Network with Sparse Strategies to Classify Dynamic Functional Connectivity

Classification of dynamic functional connectivity (DFC) is becoming a promising approach for diagnosing various neurodegenerative diseases. However, the existing methods generally face the problem of overfitting. To solve it, this paper proposes a convolutional neural network with three sparse strategies named SCNN to classify DFC. Firstly, an element-wise filter is designed to impose sparse constraints on the DFC matrix by replacing the redundant elements with zeroes, where the DFC matrix is specially constructed to quantify the spatial and temporal variation of DFC. Secondly, a 11 convolutional filter is adopted to reduce the dimensionality of the sparse DFC matrix, and remove meaningless features resulted from zero elements in the subsequent convolution process. Finally, an extra sparse optimization classifier is employed to optimize the parameters of the above two filters, which can effectively improve the ability of SCNN to extract discriminative features. Experimental results on multiple resting-state fMRI datasets demonstrate that the proposed model provides a better classification performance of DFC compared with several state-of-the-art methods, and can identify the abnormal brain functional connectivity.