基于图神经网络的自闭症辅助诊断研究综述

doi:10.19678/j.issn.1000-3428.0064352

摘要/Abstract

摘要： 自闭症谱系障碍是一种复杂的神经系统发展障碍疾病，截至目前其病因尚不明确。图神经网络作为非欧几里得空间深度学习的重要分支，在处理图结构数据的相关任务中取得优异表现，为医学领域的成像和非成像模式的集成提供了可能，因此利用图神经网络进行自闭症等脑部疾病神经成像诊断逐渐成为研究热点。阐述传统机器学习方法在自闭症疾病预测中应用，介绍图神经网络的基本分类，按照图中节点与边关系的建模方法，从基于人群图和基于个体图两个角度对图神经网络在自闭症辅助诊断中的应用进行梳理和分析，并归纳现有诊断方法的优劣势。根据目前基于图神经网络的自闭症神经成像诊断的研究现状，总结了脑神经科学领域辅助诊断技术面临的主要挑战和未来研究方向，对于自闭症等脑部疾病辅助诊断的进一步研究具有指导意义和参考价值。

关键词: 深度学习, 图神经网络, 自闭症, 辅助诊断, 磁共振成像, 神经成像

Abstract: Autistic Spectrum Disorder(ASD) is a complex neurological developmental disorder;however, its etiology remains unclear.Graph Neural Network(GNN), a branch of Deep Learning(DL) in non-Euclidean space, has excelled in a variety of tasks dealing with graph-structured data.GNN provides a universal approach for the integration of imaging and non-imaging modalities in medicine.With their development, the use of GNNs for neuroimaging diagnosis of autism and other brain diseases has gradually become a research hotspot.This paper expounds the application of traditional machine learning methods in autism disease prediction, and introduces the basic classification of GNNs.Based on the modeling approach of node-edge relationships in graphs, the application of GNNs in the auxiliary diagnosis of autism is categorized and analyzed from two perspectives:population-based and individual-based graphs, and the advantages and disadvantages of existing methods are summarized.Finally, according to the existing studies of GNN-based neuroimaging diagnosis of autism, the main challenges hampering the auxiliary diagnosis in brain neuroscience are concluded, which displays a certain guiding significance and reference value for further research on auxiliary diagnosis of autism and other brain diseases.

Key words: Deep Learning(DL), Graph Neural Network(GNN), autism, auxiliary diagnosis, Magnetic Resonance Imaging(MRI), neuroimaging

中图分类号:

TP391.7

潘嘉诚, 董一鸿, 陈华辉. 基于图神经网络的自闭症辅助诊断研究综述[J]. 计算机工程, 2022, 48(9): 1-11.

PAN Jiacheng, DONG Yihong, CHEN Huahui. Review of Research on Auxiliary Diagnosis of Autism Based on Graph Neural Networks[J]. Computer Engineering, 2022, 48(9): 1-11.

http://www.ecice06.com/CN/Y2022/V48/I9/1

图/表 5

20220917172524

20220917172528

20220917172532

20220917172536

20220917172540

参考文献

[1] KIPF T N, WELLING M.Semi-supervised classification with graph convolutional networks[EB/OL].[2022-02-08].https://arxiv.org/abs/1609.02907.
[2] VELIČKOVIĆ P, CUCURULL G, CASANOVA A, et al.Graph attention networks[EB/OL].[2022-02-08].https://zhuanlan.zhihu.com/p/345328639.
[3] XU K, LI C T, TIAN Y L, et al.Representation learning on graphs with jumping knowledge networks[EB/OL].[2022-02-08].https://arxiv.org/abs/1806.03536v2.
[4] CHO K, VAN MERRIENBOER B, GULCEHRE C, et al.Learning phrase representations using RNN encoder-decoder for statistical machine translation[C]//Proceedings of 2014 Conference on Empirical Methods in Natural Language Processing(EMNLP).Stroudsburg, USA:Association for Computational Linguistics, 2014:1-10.
[5] SHI X J, CHEN Z R, WANG H, et al.Convolutional LSTM network:a machine learning approach for precipitation nowcasting[EB/OL].[2022-02-08].https://arxiv.org/abs/1506.04214.
[6] LI Y J, TARLOW D, BROCKSCHMIDT M, et al.Gated graph sequence neural networks[EB/OL].[2022-02-08].https://arxiv.org/abs/1511.05493.
[7] LI X X, ZHOU Y, DVORNEK N C, et al.Pooling regularized graph neural network for fMRI biomarker analysis[M].Berlin, Germany:Springer, 2020.
[8] WANG M L, HUANG J S, LIU M X, et al.Modeling dynamic characteristics of brain functional connectivity networks using resting-state functional MRI[J].Medical Image Analysis, 2021, 71:102063.
[9] ORRÙ G, PETTERSSON-YEO W, MARQUAND A F, et al.Using support vector machine to identify imaging biomarkers of neurological and psychiatric disease:a critical review[J].Neuroscience & Biobehavioral Reviews, 2012, 36(4):1140-1152.
[10] MURDAUGH D L, SHINKAREVA S V, DESHPANDE H R, et al.Differential deactivation during mentalizing and classification of autism based on default mode network connectivity[J].PLoS One, 2012, 7(11):1-11.
[11] ABRAHAM A, MILHAM M P, DI MARTINO A, et al.Deriving reproducible biomarkers from multi-site resting-state data:an autism-based example[J].NeuroImage, 2017, 147:736-745.
[12] KHOSLA M, JAMISON K, KUCEYESKI A, et al.3D convolutional neural networks for classification of functional connectomes[M].Berlin, Germany:Springer, 2018.
[13] DVORNEK N C, VENTOLA P, PELPHREY K A, et al.Identifying autism from resting-state fMRI using long short-term memory networks[M].Berlin, Germany:Springer, 2017.
[14] DI MARTINO A, YAN C G, LI Q, et al.The autism brain imaging data exchange:towards a large-scale evaluation of the intrinsic brain architecture in autism[J].Molecular Psychiatry, 2014, 19(6):659-667.
[15] CAMERON C, YASSINE B, CARLTON C, et al.The neuro bureau preprocessing initiative:open sharing of preprocessed neuroimaging data and derivatives[J].Frontiers in Neuroinformatics, 2013, 7:41.
[16] CAMERON C, SHARAD S, BRIAN C, et al.Towards automated analysis of connectomes:the Configurable Pipeline for the Analysis of Connectomes(C-PAC)[J].Frontiers in Neuroinformatics, 2013, 7:42.
[17] PARISOT S, KTENA S I, FERRANTE E, et al.Spectral graph convolutions for population-based disease prediction[C]//Proceedings of International Conference on Medical Image Computing and Computer-Assisted Intervention.Berlin, Germany:Springer, 2017:177-185.
[18] PARISOT S, KTENA S I, FERRANTE E, et al.Disease prediction using graph convolutional networks:application to autism spectrum disorder and Alzheimer's disease[J].Medical Image Analysis, 2018, 48:117-130.
[19] KAZI A, SHEKARFOROUSH S, ARVIND KRISHNA S, et al.InceptionGCN:receptive field aware graph convolutional network for disease prediction[M].Berlin, Germany:Springer, 2019.
[20] CHEN L, HUANG Y M, LIAO B, et al.Graph learning approaches for graph with noise:application to disease prediction in population graph[C]//Proceedings of IEEE International Conference on Bioinformatics and Biomedicine.Washington D.C., USA:IEEE Press, 2020:2724-2729.
[21] RAKHIMBERDINA Z, MURATA T.Linear graph convolutional model for diagnosing brain disorders[C]//Proceedings of International Conference on Complex Networks and Their Applications.Berlin, Germany:Springer, 2019:815-826.
[22] ANIRUDH R, THIAGARAJAN J J.Bootstrapping graph convolutional neural networks for autism spectrum disorder classification[C]//Proceedings of 2019 IEEE International Conference on Acoustics, Speech and Signal Processing.Washington D.C., USA:IEEE Press, 2019:3197-3201.
[23] RAKHIMBERDINA Z, LIU X, MURATA T.Population graph-based multi-model ensemble method for diagnosing autism spectrum disorder[J].Sensors, 2020, 20(21):6001.
[24] HUANG Y X, CHUNG A C S.Edge-variational graph convolutional networks for uncertainty-aware disease prediction[C]//Proceedings of International Conference on Medical Image Computing and Computer-Assisted Intervention.Berlin, Germany:Springer, 2020:562-572.
[25] CHEN H, ZHUANG F Z, XIAO L, et al.AMA-GCN:adaptive multi-layer aggregation graph convolutional network for disease prediction[C]//Proceedings of the 30th International Joint Conference on Artificial Intelligence.Montreal, Canada:International Joint Conferences on Artificial Intelligence Organization, 2021:1-20.
[26] ZHENG S, ZHU Z, LIU Z, et al.Multi-modal graph learning for disease prediction[EB/OL].[2022-02-08]. https://arxiv.org/abs/2203.05880.
[27] JIANG H, CAO P, XU M Y, et al.Hi-GCN:a hierarchical graph convolution network for graph embedding learning of brain network and brain disorders prediction[J].Computers in Biology and Medicine, 2020, 127:104096.
[28] PAN L, LIU J, SHI M, et al.Identifying autism spectrum disorder based on individual-aware down-sampling and multi-modal learning[EB/OL].[2022-02-08].https://arxiv.org/abs/2109.09129v3.
[29] CAO M L, YANG M, QIN C, et al.Using DeepGCN to identify the autism spectrum disorder from multi-site resting-state data[J].Biomedical Signal Processing and Control, 2021, 70:103015.
[30] ZHOU H Y, ZHANG D Q.Graph-in-graph convolutional networks for brain disease diagnosis[C]//Proceedings of IEEE International Conference on Image Processing.Washington D.C., USA:IEEE Press, 2021:111-115.
[31] LI L, JIANG H, WEN G, et al.TE-HI-GCN:an ensemble of transfer hierarchical graph convolutional networks for disorder diagnosis[J].Neuroinformatics, 2021, 7:1-23.
[32] ARYA D, OLIJ R, GUPTA D K, et al.Fusing structural and functional MRIs using graph convolutional networks for autism classification[C]//Proceedings of the 2nd International Conference on Embedded & Distributed Systems.Washington D.C., USA:IEEE Press, 2020:44-61.
[33] FELOUAT H, OUKID-KHOUAS S.Graph convolutional networks and functional connectivity for identification of autism spectrum disorder[C]//Proceedings of the 2nd International Conference on Embedded & Distributed Systems(EDiS).Washington D.C., USA:IEEE Press, 2020:27-32.
[34] KTENA S I, PARISOT S, FERRANTE E, et al.Distance metric learning using graph convolutional networks:application to functional brain networks[C]//Proceedings of International Conference on Medical Image Computing and Computer-Assisted Intervention.Berlin, Germany:Springer, 2017:469-477.
[35] KTENA S I, PARISOT S, FERRANTE E, et al.Metric learning with spectral graph convolutions on brain connectivity networks[J].NeuroImage, 2018, 169:431-442.
[36] LOSTAR M, REKIK I.Deep hypergraph U-Net for brain graph embedding and classification[EB/OL].[2022-02-08].https://arxiv.org/abs/2008.13118.
[37] WANG L B, LI K M, HU X P.Graph convolutional network for fMRI analysis based on connectivity neighborhood[J].Network Neuroscience, 2021, 5(1):83-95.
[38] YAO D R, LIU M X, WANG M L, et al.Triplet graph convolutional network for multi-scale analysis of functional connectivity using functional MRI[C]//Proceedings of International Workshop on Graph Learning in Medical Imaging.Berlin, Germany:Springer, 2019:70-78.
[39] YANG C D, WANG P Y, TAN J, et al.autism spectrum disorder diagnosis using graph attention network based on spatial-constrained sparse functional brain networks[J].Computers in Biology and Medicine, 2021, 139:104963.
[40] LI X X, ZHOU Y, DVORNEK N, et al.BrainGNN:interpretable brain graph neural network for fMRI analysis[J].Medical Image Analysis, 2021, 74:102233.
[41] ZHAO T, LIU Y, NEVES L, et al.Data augmentation for graph neural networks[EB/OL].[2022-02-08].https://arxiv.org/abs/2006.06830v1.
[42] CHEN D L, LIN Y K, LI W, et al.Measuring and relieving the over-smoothing problem for graph neural networks from the topological view[C]//Proceedings of AAAI Conference on Artificial Intelligence.Palo Alto, USA:AAAI Press, 2020:3438-3445.
[43] CHEN Y, WU L F, ZAKI M J.Iterative deep graph learning for graph neural networks:better and robust node embeddings[C]//Proceedings of the 34th Conference on Neural Information Processing Systems.Washington D.C., USA:IEEE Press, 2020:19314-19326.
[44] BONTONOU M, FARRUGIA N, GRIPON V.Few-shot learning for decoding brain signals[EB/OL].[2022-02-08].https://arxiv.org/abs/2010.12500.
[45] ZHANG Y, BELLEC P.Transferability of brain decoding using graph convolutional networks[EB/OL].[2022-02-08].https://www.researchgate.net/publication/342368022_Transferability_of_Brain_decoding_using_Graph_Convolutional_Networks.
[46] LIBERO L E, DERAMUS T P, LAHTI A C, et al.Multimodal neuroimaging based classification of autism spectrum disorder using anatomical, neurochemical, and white matter correlates[J].Cortex, 2015, 66:46-59.
[47] YUN S, JEONG M, KIM R, et al.Graph transformer networks[EB/OL].[2022-02-08].https://arxiv.org/abs/1911.06455.
[48] QIU Y L, YU S Z, ZHOU Y H, et al.Multi-channel sparse graph transformer network for early Alzheimer's disease identification[C]//Proceedings of the 18th International Symposium on Biomedical Imaging.Washington D.C., USA:IEEE Press, 2021:1794-1797.
[49] SCHAEFER A, KONG R, GORDON E M, et al.Local-global parcellation of the human cerebral cortex from intrinsic functional connectivity MRI[J].Cerebral Cortex, 2017, 28(9):3095-3114.
[50] ZHAO K, DUKA B, XIE H, et al.A dynamic graph convolutional neural network framework reveals new insights into connectome dysfunctions in ADHD[J].NeuroImage, 2021, 246:118774.

选择文件类型/文献管理软件名称

选择包含的内容