Collaborative learning of graph generation, clustering and classification for brain networks diagnosis. (June 2022)

• Record Type: Journal Article
• Authors: Yang, Wenju; Wen, Guangqi; Cao, Peng; Yang, Jinzhu; Zaiane, Osmar R.
• Is Part Of: Computer methods and programs in biomedicine. Volume 219(2022)
• Publication Date: 2022-06
• Subjects: Autism spectrum disorder -- Functional brain networks -- Multi-graph clustering -- Generative adversarial networks -- Graph convolutional networks; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2022.106772
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: We develop a supervised multi-graph clustering for removing the noisy functional connections from the group level and identifying the critical graph structure, which actually boosts the following graph generation and classification performance. We propose a graph GAN model for augmenting the limited graph data with considering the 1) local topological measures to preserve local structural properties, 2) dual reconstruction loss to encourage a consistent generation in the graph space and 3) sample distance constraint to regularize the position of samples generated in the latent embedding space. Experimental results demonstrate that compared with the other competing models, the proposed graph GAN model can synthesize graphs that are more consistent with the original graph distribution and provide class discriminative ability. Under the help of the proposed clustering and GAN methods, the classification method not only outperforms several state-of-the-art approaches in the ASD diagnosis, but also is effective in automatically identifying disease-related subnetworks. Abstract: Purpose: Accurate diagnosis of autism spectrum disorder (ASD) plays a key role in improving the condition and quality of life for patients. In this study, we mainly focus on ASD diagnosis with functional brain networks (FBNs). The major challenge for brain networks modeling is the high dimensional connectivity in brain networks and limited number of subjects, which hinders the classification capability of graph convolutional networks (GCNs). Method: To alleviate the influence of the limited data and high dimensional connectivity, we introduce a unified three-stage graph learning framework for brain network classification, involving multi-graph clustering, graph generation and graph classification. The framework combining Graph Generation, Clustering and Classification Networks (GraphCGC-Net) enhances the critical connections by multi-graph clustering (MGC) with a supervision scheme, and generates realistic brain networks by simultaneously preserving the global consistent distribution and local topology properties. Results: To demonstrate the effectiveness of our approach, we evaluate the performance of the proposed method on the Autism Brain Imaging Data Exchange (ABIDE) dataset and conduct extensive experiments on the ASD classification problem. Our proposed method achieves an average accuracy of 70.45% and an AUC of 72.76% on ABIDE. Compared with the traditional GCN model, the proposed GraphCGC-Net obtains 9.3%, and 10.64% improvement in terms of accuracy and AUC metrics, respectively. Conclusion: The comprehensive experiments demonstrate that our GraphCGC-Net is effective for graph classification in brain disorders diagnosis. Moreover, we find that MGC can generate biologically meaningful subnetworks, which is highly consistent with the previous neuroimaging-derived biomarker evidence of ASD. More importantly, the promising results suggest that applying generative adversarial networks (GANs) in brain networks to improve the classification performance is worth further investigation.