Quantification of Cognitive Function in Alzheimer's Disease Based on Deep Learning

被引:8
作者
He, Yanxian [1 ,2 ]
Wu, Jun [2 ,3 ]
Zhou, Li [2 ,4 ]
Chen, Yi [1 ,2 ]
Li, Fang [2 ,5 ]
Qian, Hongjin [1 ,2 ]
机构
[1] PLA, Gen Hosp Southern Theater Command, Dept Cadre Ward 1, Guangzhou, Peoples R China
[2] Chinese Peoples Liberat Army Gen Hosp, Branch Natl Clin Res Ctr Geriatr Dis, Guangzhou, Peoples R China
[3] PLA, Gen Hosp Southern Theater Command, Dept Cadre Ward 3, Guangzhou, Peoples R China
[4] PLA, Gen Hosp Southern Theater Command, Dept Cadre Ward 2, Guangzhou, Peoples R China
[5] PLA, Gen Hosp Southern Theater Command, Dept Cadre Ward 4, Guangzhou, Peoples R China
关键词
Alzheimer’ s disease; quantification of cognitive function; deep separable convolution; channel pruning; convolutional neural network; NEURAL-NETWORK; DIAGNOSIS;
D O I
10.3389/fnins.2021.651920
中图分类号
Q189 [神经科学];
学科分类号
071006 ;
摘要
Alzheimer disease (AD) is mainly manifested as insidious onset, chronic progressive cognitive decline and non-cognitive neuropsychiatric symptoms, which seriously affects the quality of life of the elderly and causes a very large burden on society and families. This paper uses graph theory to analyze the constructed brain network, and extracts the node degree, node efficiency, and node betweenness centrality parameters of the two modal brain networks. The T test method is used to analyze the difference of graph theory parameters between normal people and AD patients, and brain regions with significant differences in graph theory parameters are selected as brain network features. By analyzing the calculation principles of the conventional convolutional layer and the depth separable convolution unit, the computational complexity of them is compared. The depth separable convolution unit decomposes the traditional convolution process into spatial convolution for feature extraction and point convolution for feature combination, which greatly reduces the number of multiplication and addition operations in the convolution process, while still being able to obtain comparisons. Aiming at the special convolution structure of the depth separable convolution unit, this paper proposes a channel pruning method based on the convolution structure and explains its pruning process. Multimodal neuroimaging can provide complete information for the quantification of Alzheimer's disease. This paper proposes a cascaded three-dimensional neural network framework based on single-modal and multi-modal images, using MRI and PET images to distinguish AD and MCI from normal samples. Multiple three-dimensional CNN networks are used to extract recognizable information in local image blocks. The high-level two-dimensional CNN network fuses multi-modal features and selects the features of discriminative regions to perform quantitative predictions on samples. The algorithm proposed in this paper can automatically extract and fuse the features of multi-modality and multi-regions layer by layer, and the visual analysis results show that the abnormally changed regions affected by Alzheimer's disease provide important information for clinical quantification.
引用
收藏
页数:18
相关论文
共 36 条
[1]  
[Anonymous], 2017, INT J ADV RES COMPUT, DOI DOI 10.23956/IJARCSSE/V7I6/0259
[2]   Functional Brain Network Classification for Alzheimer's Disease Detection with Deep Features and Extreme Learning Machine [J].
Bi, Xin ;
Zhao, Xiangguo ;
Huang, Hong ;
Chen, Deyang ;
Ma, Yuliang .
COGNITIVE COMPUTATION, 2020, 12 (03) :513-527
[3]   Computer aided Alzheimer's disease diagnosis by an unsupervised deep learning technology [J].
Bi, Xiuli ;
Li, Shutong ;
Xiao, Bin ;
Li, Yu ;
Wang, Guoyin ;
Ma, Xu .
NEUROCOMPUTING, 2020, 392 :296-304
[4]   Deep Learning and Random Forest Approach for Finding the Optimal Traditional Chinese Medicine Formula for Treatment of Alzheimer's Disease [J].
Chen, Hsin-Yi ;
Chen, Jian-Qiang ;
Li, Jun-Yan ;
Huang, Hung-Jin ;
Chen, Xi ;
Zhang, Hao-Ying ;
Chen, Calvin Yu-Chian .
JOURNAL OF CHEMICAL INFORMATION AND MODELING, 2019, 59 (04) :1605-1623
[5]   Deep learning only by normal brain PET identify unheralded brain anomalies [J].
Choi, Hongyoon ;
Ha, Seunggyun ;
Kang, Hyejin ;
Lee, Hyekyoung ;
Lee, Dong Soo .
EBIOMEDICINE, 2019, 43 :447-453
[6]   Predicting cognitive decline with deep learning of brain metabolism and amyloid imaging [J].
Choi, Hongyoon ;
Jin, Kyong Hwan .
BEHAVIOURAL BRAIN RESEARCH, 2018, 344 :103-109
[7]   Multimodal multitask deep learning model for Alzheimer's disease progression detection based on time series data [J].
El-Sappagh, Shaker ;
Abuhmed, Tamer ;
Islam, S. M. Riazul ;
Kwak, Kyung Sup .
NEUROCOMPUTING, 2020, 412 :197-215
[8]   Fusion of medical imaging and electronic health records using deep learning: a systematic review and implementation guidelines [J].
Huang, Shih-Cheng ;
Pareek, Anuj ;
Seyyedi, Saeed ;
Banerjee, Imon ;
Lungren, Matthew P. .
NPJ DIGITAL MEDICINE, 2020, 3 (01)
[9]   Convolutional neural network based Alzheimer's disease classification from magnetic resonance brain images [J].
Jain, Rachna ;
Jain, Nikita ;
Aggarwal, Akshay ;
Hemanth, D. Jude .
COGNITIVE SYSTEMS RESEARCH, 2019, 57 :147-159
[10]  
Jha Debesh, 2017, International Journal of Machine Learning and Computing, V7, P13, DOI 10.18178/ijmlc.2017.7.1.612