阿尔茨海默病(Alzheimer's disease, AD)是一种多见于85岁以上老人的神经系统变性疾病,其特征多表现为失语,记忆障碍等。功能性磁共振成像(functional magnetic resonance imaging,fMRI)是医生诊断AD的重要工具。目前,深度学习已在声音,图像,文字等数据领域取得突破性的进展,其在AD的fMRI图像分类中的应用也成为了研究热点。本文首先回顾了深度学习的概念;然后介绍了基于深度学习的AD的fMRI图像分类中的几种方法,包括卷积神经网络方法,循环神经网络方法,图神经网络方法;最后对未来的发展进行展望,为后续研究提供参考。
Alzheimer's disease is a neurodegenerative disease that affects people over the age of 85 and is characterised by aphasia, dyscognition and memory impairment. Functional magnetic resonance imaging is an important tool for doctors to diagnose AD. Deep learning has made breakthroughs in the field of sound, image and text data, and its application to fMRI image classification for AD has become a hot research topic. This paper first reviews the concept of deep learning; then introduces several methods in fMRI image classification for AD based on deep learning, including convolutional neural network methods, recurrent neural network methods, and graph neural network methods; and finally provides an outlook on the future development to provide reference for subsequent research.
Alzheimer's disease / Classification / Deep learning / fMRI image
表1 模型最新研究进展概括Tab.1 Overview of the latest research progress of the model |
方法 | 创新技术 | 相关研究 |
---|---|---|
卷积神经网络 | 卷积层密切连接 | [5] |
改进ResNet网络 | [6],[7] | |
循环神经网络 | 数据增强 | [9],[10] |
结合其他模型 | [10],[11] | |
池化层改进 | [14],[18] | |
结合极限学习机 | [15] | |
图神经网络 | 结合迁移学习 | [17] |
[1] | 沙小琴. 深度学习在基于fMRI图像的阿尔茨海默症分类预测中的应用研究[D]. 河北大学, 2021. |
[2] | 刘建伟, 刘媛, 罗雄麟, 等. 深度学习研究进展[J]. 计算机应用研究, 2014, 31(7): 1921-1930. |
[3] | 黄小洁. 面向任务态fMRI的深度学习建模与应用[D]. 浙江大学, 2021. |
[4] | LeCun Y, Bottou L, Bengio Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324. |
[5] | Sarraf S, Tofighi G. Deep learning-based pipeline to recognize Alzheimer's disease using fMRI data[C]. 2016 future technologies conference (FTC). IEEE, 2016: 816-820. |
[6] | Kazemi Y, Houghten S. A deep learning pipeline to classify different stages of Alzheimer's disease from fMRI data[C]. 2018 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB). IEEE, 2018: 1-8. |
[7] | Janghel RR, Rathore YK. Deep convolution neural network based system for early diagnosis of Alzheimer's disease[J]. Irbm, 2020, 1:1-10. |
[8] | Odusami M, Maskeliūnas R, Damaševičius R, et al. Analysis of features of alzheimer's disease: detection of early stage from functional brain changes in magnetic resonance images using a finetuned ResNet18 network[J]. Diagnost, 2021, 11(6): 1071. 本文引用 [1] 摘要 |
[9] | Loddo A, Buttau S, Di Ruberto C, et al. Deep learning based pipelines for Alzheimer's disease diagnosis: a comparative study and a novel deep-ensemble method[J]. Computers in Biology and Medicine, 2022, 141: 105032. |
[10] | Schuster M, Paliwal KK. Bidirectional recurrent neural networks[J]. IEEE Transactions Sign Process, 1997, 45(11): 2673-2681. |
[11] | Lin K, Jie B, Dong P, et al. Extracting Sequential Features from Dynamic Connectivity Network with rs-fMRI Data for AD Classification[C]. International Workshop on Machine Learning in Medical Imaging. Springer, Cham, 2021: 664-673. |
[12] | Sun H, Wang A, He S, et al. Temporal and Spatial Analysis of Alzheimer's Disease Based on an Improved Convolutional Neural Network and a Resting-State FMRI Brain Functional Network[J]. Int J Environment Res Pub Heal, 2022, 19(8): 4508. |
[13] | Zhang L, Wang L, Zhu D, et al. Jointly Analyzing Alzheimer's Disease Related Structure-Function Using Deep Cross-Model Attention Network[C]. 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI). IEEE, 2020: 563-567. |
[14] | Atwood J, Towsley D. Diffusion-convolutional neural networks[J]. Advanc Neur Informat Process System, 2016, 29. |
[15] | Parisot S, Ktena SI, 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. 本文引用 [2] 摘要 |
[16] | Li X, Zhou Y, Dvornek NC, et al. Pooling regularized graph neural network for fmri biomarker analysis[C]. International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, Cham, 2020: 625-635. |
[17] | Bi X, Liu Z, He Y, et al. GNEA: a graph neural network with ELM aggregator for brain network classification[J]. Complex, 2020, 2020. |
[18] | Yang C, Wang P, Tan J, et al. Autism spectrum disorder diagnosis using graph attention network based on spatial-constrained sparse functional brain networks[J]. Comput Biol Med, 2021, 139: 104963. |
[19] | Li L, Jiang H, Wen G, et al. TE-HI-GCN: an ensemble of transfer hierarchical graph convolutional networks for disorder diagnosis[J]. Neuroinform, 2021: 1-23. |
[20] | Zhu Y, Song X, Qiu Y, et al. Structure and Feature Based Graph U-Net for Early Alzheimer's Disease Prediction[C]. International Workshop on Multimodal Learning for Clinical Decision Support. Springer, Cham, 2021: 93-104. |