阿尔茨海默病的图神经网络分类方法研究进展

doi:10.19678/j.issn.1000-3428.0068719

摘要/Abstract

摘要：

阿尔茨海默病(AD)是一种不可逆的神经退行性疾病, 会导致认知能力的逐渐下降。AD症状的演变过程可能很长, 在不同的神经成像模式中可检测到脑区生物标志物的细微变化, 但其早期检测具有挑战性。由于神经成像数据的高度复杂性和大脑网络的不规则性, 传统的机器学习和深度神经网络模型存在许多不足, 开发基于图神经网络(GNN)的计算机辅助诊断(CAD)模型可以为分析非欧几里得空间的神经影像模式以及探究生物标志物提供极大帮助。首先, 对基于GNN分类方法的AD预测进行详细的调研和概述。然后, 从基于单模态数据和基于多模态数据两个视角进行梳理, 重点介绍和分析这些方法在单模态和多模态数据应用场景中的数据提取、脑网络建模、特征学习、信息融合等过程, 并评述部分方法的性能。最后, 针对GNN应用于AD诊断的主要挑战和未来研究方向进行了展望, 为AD辅助诊断的进一步研究提供有益的建议。

关键词: 图神经网络, 阿尔茨海默病, 辅助诊断, 神经成像, 多模态数据

Abstract:

Alzheimer's Disease (AD) is an irreversible neurodegenerative disorder that leads to gradual cognitive decline. The evolution of AD symptoms can be long, with subtle changes in biomarkers in brain regions that are detectable by different neuroimaging modalities; however, early detection is challenging. Given the high complexity of neuroimaging data and the irregularity of brain networks, traditional machine learning, and deep neural network models exhibit many shortcomings, and the development of Computer-Aided Diagnostic(CAD) models based on Graph Neural Network (GNN) can be beneficial for probing biomarkers and analyzing neuroimaging patterns in non-Euclidean space. First, a detailed investigation and overview of AD prediction based on GNN classification methods is carried out. Subsequently, an analysis is conducted from the two perspectives of single- and multi-modal data, with a focus on discussing and analyzing the processes of data extraction, brain network modeling, feature learning, and information fusion within the context of single- and multi-modal data applications. A performance evaluation is provided for certain methods. Finally, the primary challenges and future research directions for the application of GNNs in AD diagnosis are outlined to provide beneficial suggestions for further research on AD-assisted diagnosis.

Key words: Graph Neural Network(GNN), Alzheimer's Disease(AD), assisted diagnosis, neuroimaging, multi-modal data

顾宇衡, 潘嘉诚, 钱江波, 董一鸿. 阿尔茨海默病的图神经网络分类方法研究进展[J]. 计算机工程, 2024, 50(10): 35-50.

GU Yuheng, PAN Jiacheng, QIAN Jiangbo, DONG Yihong. Research Progress on Graph Neural Network Classification Methods for Alzheimer's Disease[J]. Computer Engineering, 2024, 50(10): 35-50.

https://www.ecice06.com/CN/Y2024/V50/I10/35

图/表 7

图1 有监督的GNN分类方法

Fig.1 Supervised GNN classification method

图2 半监督的GNN分类方法

Fig.2 Semi-supervised GNN classification method

图3 研究方法中各类数据的使用占比

Fig.3 Percentage of use of each type of data in the research methods

图4 各类方法的性能比较

Fig.4 Comparison of performance of various methods

参考文献 65

1	MCKHANN G, DRACHMAN D, FOLSTEIN M, et al. Clinical diagnosis of Alzheimer's disease: report of the NINCDS-ADRDA work group under the auspices of department of health and human services task force on Alzheimer's disease. Neurology, 1984, 34(7): 939- 944. doi: 10.1212/WNL.34.7.939
2	WEN J H, THIBEAU-SUTRE E, DIAZ-MELO M, et al. Convolutional neural networks for classification of Alzheimer's disease: overview and reproducible evaluation. Medical Image Analysis, 2020, 63, 101694. doi: 10.1016/j.media.2020.101694
3	KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks[EB/OL]. [2023-09-19]. http://arxiv.org/abs/1609.02907.
4	VELI AČG KOVIĆ P, CUCURULL G, CASANOVA A, et al. Graph attention networks[EB/OL]. [2023-09-19]. http://arxiv.org/abs/1710.10903.
5	SHI Y S, HUANG Z J, FENG S K, et al. Masked label prediction: unified message passing model for semi-supervised classification[EB/OL]. [2023-09-19]. http://arxiv.org/abs/2009.03509.
6	RATHORE S, HABES M, IFTIKHAR M A, et al. A review on neuroimaging-based classification studies and associated feature extraction methods for Alzheimer's disease and its prodromal stages. NeuroImage, 2017, 155, 530- 548. doi: 10.1016/j.neuroimage.2017.03.057
7	LIU J, LI M, LAN W, et al. Classification of Alzheimer's disease using whole brain hierarchical network. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2018, 15(2): 624- 632. doi: 10.1109/TCBB.2016.2635144
8	SUK H I, LEE S W, SHEN D G, et al. Deep ensemble learning of sparse regression models for brain disease diagnosis. Medical Image Analysis, 2017, 37, 101- 113. doi: 10.1016/j.media.2017.01.008
9	SHMULEV Y, BELYAEV M. Predicting conversion of mild cognitive impairments to Alzheimer's disease and exploring impact of neuroimaging[C]//Proceedings of Graphs in Biomedical Image Analysis and Integrating Medical Imaging and Non-Imaging Modalities: Second International Workshop, GRAIL 2018 and First International Workshop, Beyond MIC 2018, Held in Conjunction with MICCAI 2018. Berlin, Germany: Springer, 2018: 83-91.
10	BI X, LIU Z X, HE Y, et al. GNEA: a graph neural network with ELM aggregator for brain network classification[EB/OL]. [2023-09-19]. https://www.researchgate.net/publication/346576404_GNEA_A_Graph_Neural_Network_with_ELM_Aggregator_for_Brain_Network_Classification.
11	WEN G Q, CAO P, BAO H W, et al. MVS-GCN: a prior brain structure learning-guided multi-view graph convolution network for autism spectrum disorder diagnosis. Computers in Biology and Medicine, 2022, 142, 105239. doi: 10.1016/j.compbiomed.2022.105239
12	LIU M X, ZHANG H, SHI F, et al. Hierarchical graph convolutional network built by multiscale atlases for brain disorder diagnosis using functional connectivity[EB/OL]. [2023-09-19]. https://arxiv.org/abs/2209.11232.
13	LI Y, LIU J Y, JIANG Y Q, et al. Virtual adversarial training-based deep feature aggregation network from dynamic effective connectivity for MCI identification. IEEE Transactions on Medical Imaging, 2022, 41(1): 237- 251. doi: 10.1109/TMI.2021.3110829
14	CHEN D D, ZHANG L C. FE-STGNN: spatio-temporal graph neural network with functional and effective connectivity fusion for MCI diagnosis. Berlin, Germany: Springer, 2023.
15	ZHAO Y P, ZHOU F G, GUO B, et al. Spatial temporal graph convolution with graph structure self-learning for early MCI detection[C]//Proceedings of the IEEE 20th International Symposium on Biomedical Imaging (ISBI). Washington D.C., USA: IEEE Press, 2023: 1-5.
16	AN X W, ZHOU Y T, DI Y, et al. Dynamic functional connectivity and graph convolution network for Alzheimer's disease classification[C]//Proceedings of the 7th International Conference on Biomedical and Bioinformatics Engineering. New York, USA: ACM Press, 2020: 1-6.
17	KAZI A, KRISHNA S A, SHEKARFOROUSH S, et al. Self-attention equipped graph convolutions for disease prediction[C]//Proceedings of the IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019). Washington D.C., USA: IEEE Press, 2019: 1896-1899.
18	LIN H C, PAN J C, DONG Y H. Mental disorders prediction with heterogeneous graph convolutional network[C]//Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics (SMC). Washington D.C., USA: IEEE Press, 2022: 3165-3170.
19	ZHANG H, SONG R, WANG L P, et al. Classification of brain disorders in rs-fMRI via local-to-global graph neural networks. IEEE Transactions on Medical Imaging, 2023, 42(2): 444- 455. doi: 10.1109/TMI.2022.3219260
20	YAO D R, SUI J, WANG M L, et al. A mutual multi-scale triplet graph convolutional network for classification of brain disorders using functional or structural connectivity. IEEE Transactions on Medical Imaging, 2021, 40(4): 1279- 1289. doi: 10.1109/TMI.2021.3051604
21	ZHANG J, HE X H, QING L B, et al. Multi-relation graph convolutional network for Alzheimer's disease diagnosis using structural MRI. Knowledge-Based Systems, 2023, 270, 110546. doi: 10.1016/j.knosys.2023.110546
22	LENG Y L, CUI W J, BAI C, et al. Dynamic structural brain network construction by hierarchical prototype embedding GCN using T1-MRI[C]//Proceedings of International Conference on Medical Image Computing and Computer-Assisted Intervention. Berlin, Germany: Springer, 2023: 120-130.
23	VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[EB/OL]. [2023-09-19]. http://arxiv.org/abs/1706.03762.
24	ZENG L, LI H X, XIAO T S, et al. Graph convolutional network with sample and feature weights for Alzheimer's disease diagnosis. Information Processing & Management, 2022, 59(4): 102952.
25	SONG T A, CHOWDHURY S R, YANG F, et al. Graph convolutional neural networks for Alzheimer's disease classification[C]//Proceedings of the 16th International Symposium on Biomedical Imaging (ISBI 2019). Washington D.C., USA: IEEE Press, 2019: 414-417.
26	KLEPL D, HE F, WU M, et al. EEG-based graph neural network classification of Alzheimer's disease: an empirical evaluation of functional connectivity methods. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2022, 30, 2651- 2660. doi: 10.1109/TNSRE.2022.3204913
27	SHAN X C, CAO J, HUO S D, et al. Spatial-temporal graph convolutional network for Alzheimer classification based on brain functional connectivity imaging of electroencephalogram. Human Brain Mapping, 2022, 43(17): 5194- 5209. doi: 10.1002/hbm.25994
28	CAO J, YANG L, SARRIGIANNIS P G, et al. Dementia classification using a graph neural network on imaging of effective brain connectivity. Computers in Biology and Medicine, 2023, 168, 107701.
29	MENG L, ZHANG Q Q. Research on early diagnosis of Alzheimer's disease based on dual fusion cluster graph convolutional network. Biomedical Signal Processing and Control, 2023, 86, 105212. doi: 10.1016/j.bspc.2023.105212
30	LIU J, TAN G X, LAN W, et al. Identification of early mild cognitive impairment using multi-modal data and graph convolutional networks. BMC Bioinformatics, 2020, 21(6): 123.
31	SONG X G, ZHOU F, FRANGI A F, et al. Multicenter and multichannel pooling GCN for early AD diagnosis based on dual-modality fused brain network. IEEE Transactions on Medical Imaging, 2022, 42(2): 354- 367.
32	YANG Y W, YE C F, GUO X T, et al. Mapping multi-modal brain connectome for brain disorder diagnosis via cross-modal mutual learning. IEEE Transactions on Medical Imaging, 2023, 43(1): 108- 121.
33	LIN L, XIONG M, ZHANG G, et al. A convolutional neural network and graph convolutional network based framework for AD classification. Sensors, 2023, 23(4): 1914. doi: 10.3390/s23041914
34	BI X A, CHEN K, JIANG S Y, et al. Community graph convolution neural network for Alzheimer's disease classification and pathogenetic factors identification[EB/OL]. [2023-09-19]. https://www.researchgate.net/publication/370900611_Community_Graph_Convolution_Neural_Network_for_Alzheimer's_Disease_Classification_and_Pathogenetic_Factors_Identification.
35	KAZI A, SHEKARFOROUSH S, KRISHNA S A, et al. Graph convolution based attention model for personalized disease prediction[C]//Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention. Berlin, Germany: Springer, 2019: 122-130.
36	ZHENG S, ZHU Z F, LIU Z Z, et al. Multi-modal graph learning for disease prediction. IEEE Transactions on Medical Imaging, 2022, 41(9): 2207- 2216. doi: 10.1109/TMI.2022.3159264
37	YANG F S, WANG H B, WEI S C, et al. Multi-model adaptive fusion-based graph network for Alzheimer's disease prediction. Computers in Biology and Medicine, 2023, 153, 106518. doi: 10.1016/j.compbiomed.2022.106518
38	TIAN X, LIU Y, WANG L, et al. An extensible hierarchical graph convolutional network for early Alzheimer's disease identification. Computer Methods and Programs in Biomedicine, 2023, 238, 107597. doi: 10.1016/j.cmpb.2023.107597
39	ZUO Q K, LEI B Y, SHEN Y Y, et al. Multimodal representations learning and adversarial hypergraph fusion for early Alzheimer's disease prediction. Berlin, Germany: Springer, 2021.
40	KAZI A, FARGHADANI S, AGANJ I, et al. IA-GCN: interpretable attention based graph convolutional network for disease prediction. Machine Learning in Medical Imaging, 2021, 14348, 382- 392.
41	COSMO L, KAZI A, AHMADI S A, et al. Latent-graph learning for disease prediction[EB/OL]. [2023-09-19]. http://arxiv.org/abs/2003.13620.
42	PARISOT S, KTENA S I, FERRANTE E, et al. Spectral graph convolutions for population-based disease prediction. Berlin, Germany: Springer, 2017.
43	YU S Z, WANG S Q, XIAO X H, et al. Multi-scale enhanced graph convolutional network for early mild cognitive impairment detection[C]//Proceedings of International Conference on Medical Image Computing and Computer-Assisted Intervention. Berlin, Germany: Springer, 2019: 228-237.
44	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. Computers in Biology and Medicine, 2020, 127, 104096. doi: 10.1016/j.compbiomed.2020.104096
45	LOSTAR M, REKIK I. Deep hypergraph U-Net for brain graph embedding and classification[EB/OL]. [2023-09-19]. http://arxiv.org/abs/2008.13118.
46	HETT K, TA V T, OGUZ I, et al. Multi-scale graph-based grading for Alzheimer's disease prediction. Medical Image Analysis, 2021, 67, 101850. doi: 10.1016/j.media.2020.101850
47	LIU J, ZENG D J, GUO R, et al. MMHGE: detecting mild cognitive impairment based on multi-atlas multi-view hybrid graph convolutional networks and ensemble learning. Cluster Computing, 2021, 24(1): 103- 113. doi: 10.1007/s10586-020-03199-8
48	LEE J, KO W, KANG E, et al. A unified framework for personalized regions selection and functional relation modeling for early MCI identification. NeuroImage, 2021, 236, 118048. doi: 10.1016/j.neuroimage.2021.118048
49	LI H X, SHI X S, ZHU X F, et al. FSNet: dual interpretable graph convolutional network for Alzheimer's disease analysis. IEEE Transactions on Emerging Topics in Computational Intelligence, 2022, 7(1): 15- 25.
50	ALORF A, KHAN M U G. Multi-label classification of Alzheimer's disease stages from resting-state fMRI-based correlation connectivity data and deep learning. Computers in Biology and Medicine, 2022, 151, 106240. doi: 10.1016/j.compbiomed.2022.106240
51	ZUO Q K, HU J H, ZHANG Y D, et al. Brain functional network generation using distribution-regularized adversarial graph autoencoder with transformer for dementia diagnosis. Computer Modeling in Engineering & Sciences, 2023, 137(3): 2129- 2147.
52	SHI G, ZHU Y F, LIU J K, et al. HeGCL: advance self-supervised learning in heterogeneous graph-level representation[EB/OL]. [2023-09-19]. https://www.semanticscholar.org/paper/HeGCL%3A-Advance-Self-Supervised-Learning-in-Shi-Zhu/ab0aa315f5c7a00334516927fb161577952ad697.
53	KIM S, LEE N, LEE J, et al. Heterogeneous graph learning for multi-modal medical data analysis[C]//Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto, AAAI Press, 2023: 5141-5150.
54	VIVAR G, ZWERGAL A, NAVAB N, et al. Multi-modal disease classification in incomplete datasets using geometric matrix completion[C]//Proceedings of Graphs in Biomedical Image Analysis and Integrating Medical Imaging and Non-Imaging Modalities: Second International Workshop, GRAIL 2018 and First International Workshop, Beyond MIC 2018, Held in Conjunction with MICCAI 2018. Berlin, Germany: Springer, 2018: 24-31.
55	KAZI A, SHEKARFOROUSH S, ARVIND KRISHNA S, et al. InceptionGCN: receptive field aware graph convolutional network for disease prediction. Berlin, Germany: Springer, 2019.
56	HUANG Y X, CHUNG A C S. Edge-variational graph convolutional networks for uncertainty-aware disease prediction. Berlin, Germany: Springer, 2020.
57	SONG X G, FRANGI A, XIAO X H, et al. Integrating similarity awareness and adaptive calibration in graph convolution network to predict disease. Berlin, Germany: Springer, 2020.
58	ZHANG L, WANG L, GAO J, et al. Deep fusion of brain structure-function in mild cognitive impairment. Medical Image Analysis, 2021, 72, 102082. doi: 10.1016/j.media.2021.102082
59	ZUO Q K, LEI B Y, WANG S Q, et al. A prior guided adversarial representation learning and hypergraph perceptual network for predicting abnormal connections of Alzheimer's disease[EB/OL]. [2023-09-19]. http://arxiv.org/abs/2110.09302.
60	SONG X G, ZHOU F, FRANGI A F, et al. Graph convolution network with similarity awareness and adaptive calibration for disease-induced deterioration prediction. Medical Image Analysis, 2021, 69, 101947. doi: 10.1016/j.media.2020.101947
61	ZHOU H L, ZHANG Y, CHEN B Y, et al. Sparse interpretation of graph convolutional networks for multi-modal diagnosis of Alzheimer's disease[C]//Proceedings of International Conference on Medical Image Computing and Computer-Assisted Intervention. Berlin, Germany: Springer, 2022: 469-478.
62	ZHANG Y T, QING L B, HE X H, et al. Population-based GCN method for diagnosis of Alzheimer's disease using brain metabolic or volumetric features. Biomedical Signal Processing and Control, 2023, 86, 105162. doi: 10.1016/j.bspc.2023.105162
63	WANG M L, SHAO W, HUANG S, et al. Hypergraph-regularized multimodal learning by graph diffusion for imaging genetics based Alzheimer's disease diagnosis. Medical Image Analysis, 2023, 89, 102883. doi: 10.1016/j.media.2023.102883
64	FANG Y Q, WANG M L, POTTER G G, et al. Unsupervised cross-domain functional MRI adaptation for automated major depressive disorder identification. Medical Image Analysis, 2023, 84, 102707. doi: 10.1016/j.media.2022.102707
65	WANG S, ZHAO Z H, OUYANG X, et al. ChatCAD: interactive computer-aided diagnosis on medical image using large language models[EB/OL]. [2023-09-19]. https://arxiv.org/abs/2302.07257.

[1]	李泽霖, 吕兆峰, 陈富强, 李克. 基于多跳信息融合的实体对齐模型[J]. 计算机工程, 2024, 50(9): 142-152.
[2]	何杏宇, 周易歆, 罗东旭, 杨桂松. 基于图神经网络和多主体评价的教学资源推荐[J]. 计算机工程, 2024, 50(7): 13-22.
[3]	张正康, 杨丹, 聂铁铮, 寇月. 基于图结构聚类的自监督学习疾病诊断方法[J]. 计算机工程, 2024, 50(7): 360-371.
[4]	孙文洁, 李宗民, 孙浩淼. 基于图神经网络的多智能体强化学习值函数分解方法[J]. 计算机工程, 2024, 50(5): 62-70.
[5]	游奔, 李晓红, 姚锦, 冯绍杰. 基于多粒度图与注意力机制的半监督短文本分类[J]. 计算机工程, 2024, 50(5): 83-90.
[6]	张宝鑫, 杨丹, 聂铁铮, 寇月. 基于自监督的多视角图协同过滤推荐方法[J]. 计算机工程, 2024, 50(5): 100-110.
[7]	吴正洋, 张广涛, 黄立, 汤庸. 基于异质图嵌入和会话交互的课程推荐模型[J]. 计算机工程, 2024, 50(4): 95-103.
[8]	王华珍, 许泽, 孙悦, 丘斌, 陈坚, 邱强斌. 基于事件演化图的多标记事件预测模型[J]. 计算机工程, 2024, 50(4): 132-140.
[9]	吴海鹏, 钱育蓉, 冷洪勇. 基于双向注意力机制的多模态关系抽取[J]. 计算机工程, 2024, 50(4): 160-167.
[10]	王俊, 赖会霞, 万玥, 张仕. 基于角度的图神经网络高维数据异常检测方法[J]. 计算机工程, 2024, 50(3): 156-165.
[11]	王柏涵, 姜晓燕, 范柳伊. 基于深度监督隐空间构建的语义分割改进方法[J]. 计算机工程, 2024, 50(3): 191-199.
[12]	李伟健, 胡慧君. 基于潜在特征增强网络的视频描述生成方法[J]. 计算机工程, 2024, 50(2): 266-272.
[13]	吴志强, 解庆, 李琳, 刘永坚. 基于多模态融合的图神经网络推荐算法[J]. 计算机工程, 2024, 50(1): 91-100.
[14]	刘昀抒, 申彦明, 齐恒, 尹宝才. 基于层次结构图的多跳知识图谱问答模型[J]. 计算机工程, 2024, 50(1): 101-109.
[15]	顾嘉静, 杨丹, 聂铁铮, 寇月. 基于多视图融合跨层对比学习的推荐算法[J]. 计算机工程, 2024, 50(1): 120-128.

选择文件类型/文献管理软件名称

选择包含的内容