干旱区生态环境知识资源中心(Arid): Alzheimer's disease detection using depthwise separable convolutional neural networks

Arid

DOI	10.1016/j.cmpb.2021.106032
	Alzheimer's disease detection using depthwise separable convolutional neural networks
	Liu, Junxiu; Li, Mingxing; Luo, Yuling; Yang, Su; Li, Wei; Bi, Yifei
通讯作者	Luo, YL (corresponding author), Guangxi Normal Univ, Sch Elect Engn, Guilin 541004, Peoples R China.
来源期刊	COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
ISSN	0169-2607
EISSN	1872-7565
出版年	2021
卷号	203
英文摘要	To diagnose Alzheimer's disease (AD), neuroimaging methods such as magnetic resonance imaging have been employed. Recent progress in computer vision with deep learning (DL) has further inspired research focused on machine learning algorithms. However, a few limitations of these algorithms, such as the requirement for large number of training images and the necessity for powerful computers, still hinder the extensive usage of AD diagnosis based on machine learning. In addition, large number of training parameters and heavy computation make the DL systems difficult in integrating with mobile embedded devices, for example the mobile phones. For AD detection using DL, most of the current research solely focused on improving the classification performance, while few studies have been done to obtain a more compact model with less complexity and relatively high recognition accuracy. In order to solve this problem and improve the efficiency of the DL algorithm, a deep separable convolutional neural network model is proposed for AD classification in this paper. The depthwise separable convolution (DSC) is used in this work to replace the conventional convolution. Compared to the traditional neural networks, the parameters and computing cost of the proposed neural network are found greatly reduced. The parameters and computational costs of the proposed neural network are found to be significantly reduced compared with conventional neural networks. With its low power consumption, the proposed model is particularly suitable for embedding mobile devices. Experimental findings show that the DSC algorithm, based on the OASIS magnetic resonance imaging dataset, is very successful for AD detection. Moreover, transfer learning is employed in this work to improve model performance. Two trained models with complex networks, namely AlexNet and GoogLeNet, are used for transfer learning, with average classification rates of 91.40%, 93.02% and a less power consumption. (c) 2021 Elsevier B.V. All rights reserved.
英文关键词	Depthwise separable convolution Alzheimer's disease Deep learning Transfer learning
类型	Article
语种	英语
收录类别	SCI-E
WOS记录号	WOS:000639852700004
WOS关键词	MILD COGNITIVE IMPAIRMENT ; CLASSIFICATION ; PREDICTION ; MRI ; CONVERSION ; BIOMARKER ; ATROPHY ; MODELS
WOS类目	Computer Science, Interdisciplinary Applications ; Computer Science, Theory & Methods ; Engineering, Biomedical ; Medical Informatics
WOS研究方向	Computer Science ; Engineering ; Medical Informatics
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/349882
作者单位	[Liu, Junxiu; Li, Mingxing; Luo, Yuling] Guangxi Normal Univ, Sch Elect Engn, Guilin 541004, Peoples R China; [Yang, Su] Univ West London, Sch Comp & Engn, London, England; [Li, Wei] Fudan Univ, Acad Engn & Technol, Shanghai, Peoples R China; [Bi, Yifei] Univ Shanghai Sci & Technol, Coll Foreign Languages, Shanghai, Peoples R China
推荐引用方式 GB/T 7714	Liu, Junxiu,Li, Mingxing,Luo, Yuling,et al. Alzheimer's disease detection using depthwise separable convolutional neural networks[J],2021,203.
APA	Liu, Junxiu,Li, Mingxing,Luo, Yuling,Yang, Su,Li, Wei,&Bi, Yifei.(2021).Alzheimer's disease detection using depthwise separable convolutional neural networks.COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE,203.
MLA	Liu, Junxiu,et al."Alzheimer's disease detection using depthwise separable convolutional neural networks".COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 203(2021).