MVS-GCN: A prior brain structure learning-guided multi-view graph convolution network for autism spectrum disorder diagnosis

Wen, Guangqi; Cao, Peng; Bao, Huiwen; Yang, Wenju; Zheng, Tong; Zaı̈ane, Osmar R.

doi:10.1016/j.compbiomed.2022.105239

Cited by 97 publications

(29 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another possible reason is that our approach takes into account the complementary information of FBNs generated by different estimation methods. We can also see that our method compares to achieves better classification performance than the four deep fusion methods (i.e., GraphCGC-Net [ 51 ], MVS-GCN [ 30 ], MFC-PL [ 52 ], and BrainGC-Net [ 53 ]), with improvements of

and

in terms of ACC and AUC, respectively. This is possible because deep fusion methods tend to rely on a large amount of data [ 51 ], whereas this study includes a limited number of subjects.…”

Section: Methodsmentioning

confidence: 94%

“…It further finetunes the pretrained GCN by combining the generated and original graphs into a mixed training dataset. MVS-GCN [ 30 ]: This method is a prior brain structure learning-guided multiview graph convolution network framework. It first constructs multiview coarsened brain network structures that are consistent for all the subjects and then implements multitask graph embedding learning to capture the intrinsic correlations among different views.…”

Section: Methodsmentioning

confidence: 99%

“…Among the abovementioned methods, MNER [ 26 ], LORTA [ 46 ], and BMGF [ 27 ] are shallow fusion methods, whereas GraphCGC-Net [ 51 ], MVS-GCN [ 30 ], MFC-PL [ 52 ], and BrainGC-Net [ 53 ] are deep fusion approaches.…”

Section: Methodsmentioning

confidence: 99%

“…Although they can estimate FBNs well in some scenarios, these methods only consider the association between ROIs from a single perspective, thus failing to capture the complex interactions among ROIs in the brain. To obtain effective representations of brain fMRI, several previous studies attempted to fuse multiview FBNs derived from rs-fMRI using different FBN estimation strategies [ 25 , 26 , 27 , 28 , 29 , 30 ]. For instance, Jie et al [ 25 ] proposed thresholding of brain FBNs constructed using the PC method to generate multiple thresholded FBNs, followed by a multiple-kernel learning method to combine features of these FBNs for classification.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Fusing Multiview Functional Brain Networks by Joint Embedding for Brain Disease Identification

Wang

Zhang

et al. 2023

JPM

View full text Add to dashboard Cite

Background: Functional brain networks (FBNs) derived from resting-state functional MRI (rs-fMRI) have shown great potential in identifying brain disorders, such as autistic spectrum disorder (ASD). Therefore, many FBN estimation methods have been proposed in recent years. Most existing methods only model the functional connections between brain regions of interest (ROIs) from a single view (e.g., by estimating FBNs through a specific strategy), failing to capture the complex interactions among ROIs in the brain. Methods: To address this problem, we propose fusion of multiview FBNs through joint embedding, which can make full use of the common information of multiview FBNs estimated by different strategies. More specifically, we first stack the adjacency matrices of FBNs estimated by different methods into a tensor and use tensor factorization to learn the joint embedding (i.e., a common factor of all FBNs) for each ROI. Then, we use Pearson’s correlation to calculate the connections between each embedded ROI in order to reconstruct a new FBN. Results: Experimental results obtained on the public ABIDE dataset with rs-fMRI data reveal that our method is superior to several state-of-the-art methods in automated ASD diagnosis. Moreover, by exploring FBN “features” that contributed most to ASD identification, we discovered potential biomarkers for ASD diagnosis. The proposed framework achieves an accuracy of 74.46%, which is generally better than the compared individual FBN methods. In addition, our method achieves the best performance compared to other multinetwork methods, i.e., an accuracy improvement of at least 2.72%. Conclusions: We present a multiview FBN fusion strategy through joint embedding for fMRI-based ASD identification. The proposed fusion method has an elegant theoretical explanation from the perspective of eigenvector centrality.

show abstract

and

in terms of ACC and AUC, respectively. This is possible because deep fusion methods tend to rely on a large amount of data [ 51 ], whereas this study includes a limited number of subjects.…”

Section: Methodsmentioning

confidence: 94%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Fusing Multiview Functional Brain Networks by Joint Embedding for Brain Disease Identification

Wang

Zhang

et al. 2023

JPM

View full text Add to dashboard Cite

show abstract

“…[4] used GCN to fuse structural and functional MRI for ASD classification. Additionally, many improved versions based on GCN were also developed from multi-layer [5, 6] and multi-view [7, 8] to detect brain diseases. Unlike traditional classifiers that are trained directly by the adjacency matrices of BFNs, the GCN-based classification methods need the node feature matrix as an extra input.…”

Section: Introductionmentioning

confidence: 99%

The Effect of Node Features on GCN-based Brain Network Classification: An Empirical Study

Wang

Zhang

Qiao

2022

Preprint

View full text Add to dashboard Cite

Brain functional network (BFN) analysis has become a popular technique for identifying neurological/mental diseases. Due to the fact that BFN is a graph, graph convolutional network (GCN) can be naturally used in the classification of BFN. Different from traditional methods that directly use the adjacency matrices of BFNs to train a classifier, GCN requires an additional input i.e.,node features. To our best knowledge, however, there is no systematic study to analyze their influence on the performance of GCN-based brain disorder classification. Therefore, in this per, we conduct an empirical study on various node feature measures, including 1) original fMRI signals, 2) one-hot encoding, 3) node statistics, 4) node correlation, and 5) their combination. Experimental results on two benchmark databases show that different node feature inputs to GCN significantly affect the brain disease classification performance, and node correlation usually contributes higher accuracy compared to original signals and manually extracted statistical features.

show abstract

MTGWNN: A Multi‐Template Graph Wavelet Neural Network Identification Model for Autism Spectrum Disorder

Shan,

Ren,

Jiao

et al. 2024

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Functional magnetic resonance imaging (fMRI) has been widely applied in studying various brain disorders. However, current studies typically model regions of interest (ROIs) in brains with a single template. This approach generally examines only the connectivity between ROIs to identify autism spectrum disorder (ASD), ignoring the structural features of the brain. This study proposes a multi‐template graph wavelet neural network (GWNN) identification model for ASD called MTGWNN. First, the brain is segmented with multiple templates and the BOLD time series are extracted from fMRI data to construct brain networks. Next, a graph attention network (GAT) is applied to automatically learn interactions between nodes, capturing local information in the node features. These features are then further processed by a convolutional neural network (CNN) to learn global connectivity representations and achieve feature dimensionality reduction. Finally, the features and phenotypic data from each subject are integrated by GWNN to identify ASD at the optimal scale. Experimental results indicate that MTGWNN outperforms the comparative models. Testing on the public dataset ABIDE‐I achieved an accuracy (ACC) of 87.25% and an area under the curve (AUC) of 92.49%. MTGWNN effectively integrates brain network features from multiple templates, providing a more comprehensive characterization of brain abnormalities in patients with ASD. It incorporates population information from phenotypic data, which helps to compensate for the limited sample size of individual patients and improves the robustness and generalization of ASD identification.

show abstract

MVS-GCN: A prior brain structure learning-guided multi-view graph convolution network for autism spectrum disorder diagnosis

Cited by 97 publications

References 32 publications

Fusing Multiview Functional Brain Networks by Joint Embedding for Brain Disease Identification

Fusing Multiview Functional Brain Networks by Joint Embedding for Brain Disease Identification

The Effect of Node Features on GCN-based Brain Network Classification: An Empirical Study

MTGWNN: A Multi‐Template Graph Wavelet Neural Network Identification Model for Autism Spectrum Disorder

Contact Info

Product

Resources

About