干旱区生态环境知识资源中心(Arid): Parameter Combination Optimization in Three-Dimensional Convolutional Neural Networks and Transfer Learning for Detecting Alzheimer's Disease from Magnetic Resonance Images

Arid

DOI	10.18494/SAM3923
	Parameter Combination Optimization in Three-Dimensional Convolutional Neural Networks and Transfer Learning for Detecting Alzheimer's Disease from Magnetic Resonance Images
	Lin, Cheng-Jian; Lin, Tzu-Chao; Lin, Cheng-Wei
通讯作者	Lin, CJ
来源期刊	SENSORS AND MATERIALS
ISSN	0914-4935
出版年	2022
卷号	34 期号:7 页码:2837-2851
英文摘要	Alzheimer's disease (AD) destroys neurons in the brain, engendering brain atrophy and severely compromising brain function. Magnetic resonance imaging (MRI) is widely applied to analyze brain degeneration. AD is typically detected by examining specialist-selected features of two-dimensional images or region-of-interest features identified by trained classifiers. We developed a Taguchi-based three-dimensional convolutional neural network (T-3D-CNN) model for detecting AD in magnetic resonance images. CNN parameters are generally obtained through trial-and-error methods. To stabilize the CNN diagnostic accuracy, the Taguchi method was employed for parameter combination optimization. Obtaining patient data is difficult; thus, we performed transfer learning to verify the proposed T-3D-CNN model's effectiveness by using only a small quantity of patient data from various databases. The experimental results confirmed that the T-3D-CNN model detected AD from images in the Open Access Series of Imaging Studies (OASIS)-2 data set with an accuracy of 99.46%, which was 2.06 percentage points higher than that of the original 3D-CNN. After a complete investigation of the OASIS-2 data set, we selected 10, 30, 60, 80, and 100% of the data from the OASIS-1 data set to verify the T-3D-CNN and updated the original network weights through transfer learning; the average accuracies were 81.31, 92.88, 95.85, 100, and 100%, respectively.
英文关键词	Alzheimer's disease magnetic resonance imaging three-dimensional convolutional neural networks Taguchi experimental design transfer learning
类型	Article
语种	英语
开放获取类型	gold
收录类别	SCI-E
WOS记录号	WOS:000834301400001
WOS关键词	OPEN ACCESS SERIES ; MRI DATA ; DIAGNOSIS
WOS类目	Instruments & Instrumentation ; Materials Science, Multidisciplinary
WOS研究方向	Instruments & Instrumentation ; Materials Science
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/394490
推荐引用方式 GB/T 7714	Lin, Cheng-Jian,Lin, Tzu-Chao,Lin, Cheng-Wei. Parameter Combination Optimization in Three-Dimensional Convolutional Neural Networks and Transfer Learning for Detecting Alzheimer's Disease from Magnetic Resonance Images[J],2022,34(7):2837-2851.
APA	Lin, Cheng-Jian,Lin, Tzu-Chao,&Lin, Cheng-Wei.(2022).Parameter Combination Optimization in Three-Dimensional Convolutional Neural Networks and Transfer Learning for Detecting Alzheimer's Disease from Magnetic Resonance Images.SENSORS AND MATERIALS,34(7),2837-2851.
MLA	Lin, Cheng-Jian,et al."Parameter Combination Optimization in Three-Dimensional Convolutional Neural Networks and Transfer Learning for Detecting Alzheimer's Disease from Magnetic Resonance Images".SENSORS AND MATERIALS 34.7(2022):2837-2851.