A Prior Causality-Guided Multi-View Diffusion Network for Brain Disorder Classification

Abstract

Functional brain networks have been used to diagnose brain disorders such as autism spectrum disorder (ASD) and attention-deficit/hyperactivity disorder (ADHD). However, existing methods not only fail to fully consider various levels of interaction information between brain regions, but also limit the transmission of information among unconnected regions, resulting in the node information loss and bias. To address these issues, we propose a causality-guided multi-view diffusion (CG-MVD) network, which can more comprehensively capture node information that is difficult to observe when aggregating direct neighbours alone. Specifically, our approach designs multi-view brain graphs and multi-hop causality graphs to represent multi-level node interactions and guide the diffusion of interaction information. Building on this, a multi-view diffusion graph attention module is put forward to learn node multi-dimensional embedding features by broadening the interaction range and extending the receptive field. Additionally, we propose a bilinear adaptive fusion module to generate and fuse connectivity-based features, addressing the challenge of high-dimensional node-level features and integrating richer feature information to enhance classification. Experimental results on the ADHD-200 and ABIDE-I datasets demonstrate the effectiveness of the CG-MVD network, achieving average accuracies of 79.47% and 80.90%, respectively, and surpassing state-of-the-art methods.

Keywords

bioinformatics / data analysis / deep learning / image classification

References

[1] E. Bullmore and O. Sporns, “Complex Brain Networks: Graph Theoretical Analysis of Structural and Functional Systems,” Nature Reviews Neuroscience 10, no. 3 (2009): 186-198, https://doi.org/10.1038/nrn2575.

[2] N. C. Dvornek, P. Ventola, and J. S. Duncan, “Combining Phenotypic and Resting-State fMRI Data for Autism Classification With Recurrent Neural Networks,” in 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI)IEEE, 2018).

[3] H. Jiang, P. Cao, M. Xu, J. Yang, and O. Zaiane, “Hi-GCN: A Hierar-chical Graph Convolution Network for Graph Embedding Learning of Brain Network and Brain Disorders Prediction,” Computers in Biology and Medicine 127 (2020): 104096, https://doi.org/10.1016/j.compbiomed.2020.104096.

[4] Z. Lan, Y. Sun, L. Zhao, Y. Xiao, C. Kuai, and S. W. Xue, “Aberrant Effective Connectivity of the Ventral Putamen in Boys With Attention-Deficit/Hyperactivity Disorder,” Psychiatry Investigation 18, no. 8 (2021):763-769, https://doi.org/10.30773/pi.2020.0422.

[5] M. Khosla, K. Jamison, G. H. Ngo, A. Kuceyeski, and M. R. Sabuncu, “Machine Learning in Resting-State fMRI Analysis,” Magnetic Reso-nance Imaging 64 (2019): 101-121, https://doi.org/10.1016/j.mri.2019.05.031.

[6] M. Wang, X. Hao, J. Huang, et al., “Hierarchical Structured Sparse Learning for Schizophrenia Identification,” Neuroinformatics 18, no. 1 (2020): 43-57, https://doi.org/10.1007/s12021-019-09423-0.

[7] J. Kawahara, C. J. Brown, S. P. Miller, et al., “BrainNetCNN: Con-volutional Neural Networks for Brain Networks Towards Predicting Neurodevelopment,” NeuroImage 146 (2017): 1038-1049, https://doi.org/10.1016/j.neuroimage.2016.09.046.

[8] J. Deng, M. R. Hasan, M. M. Mahmud, et al., “Diagnosing Autism Spectrum Disorder Using Ensemble 3D-CNN: A Preliminary Study,” in 2022 IEEE International Conference on Image Processing (ICIP)IEEE, 2022).

[9] S. De Silva, S. U. Dayarathna, G. Ariyarathne, D. Meedeniya, and S. Jayarathna, “fMRI Feature Extraction Model for ADHD Classification Using Convolutional Neural Network,” International Journal of E-Health and Medical Communications 12, no. 1 (2021): 81-105, https://doi.org/10.4018/ijehmc.2021010106.

[10] Y. Liu, L. He, B. Cao, et al., “Multi-View Multi-Graph Embedding for Brain Network Clustering Analysis,” in Proceedings of the AAAI Conference on Artificial Intelligence (2018).

[11] J. Atwood and D. Towsley, “Diffusion-Convolutional Neural Net-works,” Advances in Neural Information Processing Systems 29 (2016).

[12] S. Agarwal, A. Raj, A. Chowdhury, G. Aich, R. Chatterjee, and K. Ghosh, “Investigating the Impact of Standard Brain Atlases and Con-nectivity Measures on the Accuracy of ADHD Detection From fMRI Data Using Deep Learning,” Multimedia Tools and Applications 83, no. 25 (2024): 1-35, https://doi.org/10.1007/s11042-023-17962-7.

[13] Y. Li, H. Liu, and B. Yang, “STNet: Deep Audio-Visual Fusion Network for Robust Speaker Tracking,” IEEE Transactions on Multi-media (2024): 1-13.

[14] S. Parisot, S. I. Ktena, E. Ferrante, et al., “Disease Prediction Using Graph Convolutional Networks: Application to Autism Spectrum Dis-order and Alzheimer’s Disease,” Medical Image Analysis 48 (2018): 117-130, https://doi.org/10.1016/j.media.2018.06.001.

[15] Y. Feng, H. You, Z. Zhang, et al. “Hypergraph Neural Networks ” , in Proceedings of the AAAI Conference on Artificial Intelligence (2019).

[16] X. Li, Y. Zhou, N. Dvornek, et al., “BrainGNN: Interpretable Brain Graph Neural Network for fMRI Analysis,” Medical Image Analysis 74 (2021): 102233, https://doi.org/10.1016/j.media.2021.102233.

[17] D. Yan, S. Wu, M. T. Sami, et al., “Improving Brain Dysfunction Prediction by GAN: A Functional-Connectivity Generator Approach,” in 2021 IEEE International Conference on Big Data (Big Data)IEEE, 2021).

[18] Y. Yang, C. Ye, and T. Ma, “A Deep Connectome Learning Network Using Graph Convolution for Connectome-Disease Association Study,” Neural Networks 164 (2023): 91-104, https://doi.org/10.1016/j.neunet.2023.04.025.

[19] P. Veličković, G. Cucurull, A. Casanova, et al. “Graph Attention Networks ” , ArXiv Preprint ArXiv:1710. 10903 (2017).

[20] W. Chen, J. Yang, Z. Sun, et al., “DeepASD: A Deep Adversarial-Regularized Graph Learning Method for ASD Diagnosis With Multi-modal Data,” Translational Psychiatry 14, no. 1 (2024): 375, https://doi.org/10.1038/s41398-024-02972-2.

[21] N. A. Khan and X. Shang, “ASD-GANNet: A Generative Adversarial Network-Inspired Deep Learning Approach for the Classification of Autism Brain Disorder,” Brain Sciences 14, no. 8 (2024): 766, https://doi.org/10.3390/brainsci14080766.

[22] Y. Li, H. Liu, and H. Tang, “Multi-Modal Perception Attention Network With Self-Supervised Learning for Audio-Visual Speaker Tracking,” in Proceedings of the AAAI Conference on Artificial Intelli-gence, (2022).

[23] R. Milo, S. Shen-Orr, S. Itzkovitz, N. Kashtan, D. Chklovskii, and U. Alon, “Network Motifs: Simple Building Blocks of Complex Networks,” Science 298, no. 5594 (2002): 824-827, https://doi.org/10.1126/science.298.5594.824.

[24] O. Sporns and R. Kötter, “Motifs in Brain Networks ” PLoS Biology 2, no. 11 (2004): e369, https://doi.org/10.1371/journal.pbio.0020369.

[25] A. R. Benson, D. F. Gleich, and J. Leskovec, “Higher-Order Orga-nization of Complex Networks,” Science 353, no. 6295 (2016): 163-166, https://doi.org/10.1126/science.aad9029.

[26] P.-Z. Li Y. X. Cai C. D. Wang M. J. Liang and Y. Q. Zheng, “Higher-Order Brain Network Analysis for Auditory Disease,” Neural Processing Letters 49, no. 3 (2019): 879-897, https://doi.org/10.1007/s11063-018-9815-7.

[27] L. Wang, J. Ren, B. Xu, J. Li, W. Luo, and F. Xia, “Model: Motif-Based Deep Feature Learning for Link Prediction,” IEEE Transactions on Computational Social Systems 7, no. 2 (2020): 503-516, https://doi.org/10.1109/tcss.2019.2962819.

[28] J. B. Lee, R. A. Rossi, X. Kong, et al., “Graph Convolutional Net-works With Motif-Based Attention,” in Proceedings of the 28th ACM International Conference on Information and Knowledge Management (2019).

[29] H. Peng, J. Li, Q. Gong, et al., “Motif-Matching Based Subgraph-Level Attentional Convolutional Network for Graph Classification,” in Proceedings of the AAAI Conference on Artificial Intelligence (2020).

[30] X. Li, W. Wei, X. Feng, X. Liu, and Z. Zheng, “Representation Learning of Graphs Using Graph Convolutional Multilayer Networks Based on Motifs,” Neurocomputing 464 (2021): 218-226, https://doi.org/10.1016/j.neucom.2021.08.028.

[31] G. Nikolentzos, G. Dasoulas and M. Vazirgiannis, “k-Hop Graph Neural Networks,” Neural Networks 130 (2020): 195-205, https://doi.org/10.1016/j.neunet.2020.07.008.

[32] H. He, H. Niu, J. Feng, J. Nie, Y. Zhang, and J. Ren, “An Embedding Model for Knowledge Graph Completion Based on Graph Sub-Hop Convolutional Network,” Big Data Research 30 (2022): 100351, https://doi.org/10.1016/j.bdr.2022.100351.

[33] S. Abu-El-Haija, B. Perozzi, A. Kapoor, et al., “Mixhop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing,” in International Conference on Machine Learning (PMLR, 2019).

[34] X. Fan, M. Gong, and Y. Wu, “Markov Clustering Regularized Multi-Hop Graph Neural Network,” Pattern Recognition 139 (2023): 109518, https://doi.org/10.1016/j.patcog.2023.109518.

[35] T. Yao, Y. Wang, K. Zhang, et al., “Improving the Expressiveness of K-Hop Message-Passing GNNs by Injecting Contextualized Substructure Information,” in Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (2023).

[36] J. Chen, Z. Li, Y. Zhu, et al., “From Node Interaction to Hop Interaction: New Effective and Scalable Graph Learning Paradigm,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2023).

[37] N. Tzourio-Mazoyer, B. Landeau, D. Papathanassiou, et al., “Auto-mated Anatomical Labeling of Activations in SPM Using a Macroscopic Anatomical Parcellation of the MNI MRI Single-Subject Brain,” Neu-roImage 15, no. 1 (2002): 273-289, https://doi.org/10.1006/nimg.2001.0978.

[38] S. Bajaj, B. M. Adhikari, K. J. Friston, and M. Dhamala, “Bridging the Gap: Dynamic Causal Modeling and Granger Causality Analysis of Resting State Functional Magnetic Resonance Imaging,” Brain Con-nectivity 6, no. 8 (2016): 652-661, https://doi.org/10.1089/brain.2016.0422.

[39] S. L. Bressler and A. K. Seth, “Wiener-Granger Causality: A Well Established Methodology,” NeuroImage 58, no. 2 (2011): 323-329, https://doi.org/10.1016/j.neuroimage.2010.02.059.

[40] J. Meier, M. Märtens, A. Hillebrand, et al., “Motif-Based Analysis of Effective Connectivity in Brain Networks,” in Complex Networks & Their Applications V: Proceedings of the 5th International Workshop on Com-plex Networks and Their Applications (COMPLEX NETWORKS 2016)Springer, 2017).

[41] S. Wernicke and F. Rasche, “FANMOD: A Tool for Fast Network Motif Detection,” Bioinformatics 22, no. 9 (2006): 1152-1153, https://doi.org/10.1093/bioinformatics/btl038.

[42] Y. Wei, X. Liao, C. Yan, Y. He, and M. Xia, “Identifying Topological Motif Patterns of Human Brain Functional Networks,” Human Brain Mapping 38, no. 5 (2017): 2734-2750, https://doi.org/10.1002/hbm.23557.

[43] J. H. Zhang Jianxu, S. Hu, and X. Wang, “Traffic Parameter Pre-diction Based on Multi-Factor Fusion Spatio-Temporal Graph Neural Network,” Journal of Chongqing University of Technology 37, no. 8 (2023): 185-193.

[44] J. Huang, L. Zhou, L. Wang, and D. Zhang, “Attention-Diffusion-Bilinear Neural Network for Brain Network Analysis,” IEEE Trans-actions on Medical Imaging 39, no. 7 (2020): 2541-2552, https://doi.org/10.1109/tmi.2020.2973650.

[45] T.-Y. Lin A. RoyChowdhury and S. Maji, “Bilinear CNN Models for Fine-Grained Visual Recognition,” in Proceedings of the IEEE Interna-tional Conference on Computer Vision (2015).

[46] S. Zou, X. Huang, X. Shen, and H. Liu, “Improving Multimodal Fusion With Main Modal Transformer for Emotion Recognition in Conversation,” Knowledge-Based Systems 258 (2022): 109978, https://doi.org/10.1016/j.knosys.2022.109978.

[47] Z. Chen, C. Zhou, and Y. Zhou, “A Hierarchical Federated Learning Model With Adaptive Model Parameter Aggregation,” Computer Science and Information Systems 20, no. 3 (2023): 1037-1060, https://doi.org/10.2298/csis220930026c.

[48] W. Y. Xu Chuanyun, W. A. N. G. Wenmin, L. I. Gang, Z. H. E. N. Yu, and Q. Zhang, “Multi-Level Features Weighted Fusion Algorithm for Domestic Garbage Image Classification,” Journal of Chongqing University of Technology 36, no. 9 (2022): 146-155.

[49] A. Consortium, “A Model to Advance the Translational Potential of Neuroimaging in Clinical Neuroscience,” Frontiers in Systems Neuro-science 6 (2012): 62, https://doi.org/10.3389/fnsys.2012.00062.

[50] A. Di Martino, C. G. Yan, Q. Li, et al., “The Autism Brain Imaging Data Exchange: Towards a Large-Scale Evaluation of the Intrinsic Brain Architecture in Autism,” Molecular Psychiatry 19, no. 6 (2014): 659-667, https://doi.org/10.1038/mp.2013.78.

Funding

National Natural Science Foundation of China(Grants 62376184)

National Natural Science Foundation of China(62403345)

Central Guided Local Science and Technology Development Project(Grant YDZJSX20231A017)

Shanxi Provincial Department of Science and Technology Basic Research Project(Grants 202403021212174)

Shanxi Provincial Department of Science and Technology Basic Research Project(20210302124550)

Shanxi Provincial Special Guidance Programme for the Transformation of Scientific and Technological Achievements(Grants 202404021301032)

Shanxi Provincial Special Guidance Programme for the Transformation of Scientific and Technological Achievements(202304021301035)