Polar-Net: A Clinical-Friendly Model for Alzheimer's Disease Detection in OCTA Images

doi:10.1007/978-3-031-43990-2_57

科研成果详情

题名	Polar-Net: A Clinical-Friendly Model for Alzheimer's Disease Detection in OCTA Images
作者	Liu, Shouyue1,2; Hao, Jinkui 1; Xu, Yanwu 3,4; Fu, Huazhu 5; Guo, Xinyu 1; Liu, Jiang 6; Zheng, Yalin 7; Liu, Yonghuai 8; Zhang, Jiong 1; Zhao, Yitian 1
会议录名称	SPRINGER INTERNATIONAL PUBLISHING AG 影响因子和分区
语种	英语
原始文献类型	Proceedings Paper ; Conference Paper
会议名称	26th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI)
会议日期	OCT 08-12, 2023
会议地点	Vancouver, CANADA
关键词	OCTA Alzheimer's Disease Polar Transformation Alzheimer’s Disease
其他关键词	SEGMENTATION ; NETWORK
摘要	Optical Coherence Tomography Angiography (OCTA) is a promising tool for detecting Alzheimer's disease (AD) by imaging the retinal microvasculature. Ophthalmologists commonly use region-based analysis, such as the ETDRS grid, to study OCTA image biomarkers and understand the correlation with AD. In this work, we propose a novel deep-learning framework called Polar-Net. Our approach involves mapping OCTA images from Cartesian coordinates to polar coordinates, which allows for the use of approximate sector convolution and enables the implementation of the ETDRS grid-based regional analysis method commonly used in clinical practice. Furthermore, Polar-Net incorporates clinical prior information of each sector region into the training process, which further enhances its performance. Additionally, our framework adapts to acquire the importance of the corresponding retinal region, which helps researchers and clinicians understand the model's decision-making process in detecting AD and assess its conformity to clinical observations. Through evaluations on private and public datasets, we have demonstrated that Polar-Net outperforms existing state-of-the-art methods and provides more valuable pathological evidence for the association between retinal vascular changes and AD. In addition, we also show that the two innovative modules introduced in our framework have a significant impact on improving overall performance.
资助项目	A*STAR[A20H4b0141];National Science Foundation Program of China[62103398,62272444];Zhejiang Provincial Natural Science Foundation of China[LR22F020008];Youth Innovation Promotion Association CAS[2021298]
出版地	CHAM
出版者	Springer Science and Business Media Deutschland GmbH
ISSN	0302-9743
EISSN	1611-3349
卷号	14226 LNCS
页码	607-617
DOI	10.1007/978-3-031-43990-2_57
页数	11
URL	查看原文
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Theory & Methods ; Radiology, Nuclear Medicine & Medical Imaging
WOS研究方向	Computer Science ; Radiology, Nuclear Medicine & Medical Imaging
WOS记录号	WOS:001109636000057
收录类别	CPCI ; CPCI-S ; SCOPUS ; EI
发表日期	2023
EI入藏号	20234314954944
EI主题词	Optical tomography
EI分类号	403.2 Regional Planning and Development ; 461.4 Ergonomics and Human Factors Engineering ; 461.6 Medicine and Pharmacology ; 723.5 Computer Applications ; 741.3 Optical Devices and Systems ; 901.2 Education ; 912.2 Management
通讯作者地址	[Zhao, Yitian]Chinese Acad Sci, Ningbo Inst Mat Technol & Engn, Cixi Inst Biomed Engn, Ningbo, Peoples R China. ; [Xu, Yanwu]South China Univ Technol, Sch Future Technol, Guangzhou, Peoples R China. ; [Xu, Yanwu]Pazhou Lab, Guangzhou, Peoples R China.
Scopus记录号	2-s2.0-85174726385
Scopus学科分类	Theoretical Computer Science;Computer Science (all)
引用统计
文献类型	会议论文
条目标识符	https://kms.wmu.edu.cn/handle/3ETUA0LF/205671
专题	其他_温州医科大学慈溪生物医药研究院
通讯作者	Xu, Yanwu; Zhao, Yitian
作者单位	1.Chinese Acad Sci, Ningbo Inst Mat Technol & Engn, Cixi Inst Biomed Engn, Ningbo, Peoples R China; 2.Wenzhou Med Univ, Cixi Biomed Res Inst, Ningbo, Peoples R China; 3.South China Univ Technol, Sch Future Technol, Guangzhou, Peoples R China; 4.Pazhou Lab, Guangzhou, Peoples R China; 5.ASTAR, Inst High Performance Comp, Singapore, Singapore; 6.Southern Univ Sci & Technol, Dept Comp Sci, Shenzhen, Peoples R China; 7.Univ Liverpool, Dept Eye & Vis Sci, Liverpool, Merseyside, England; 8.Edge Hill Univ, Dept Comp Sci, Ormskirk, England
第一作者单位	其他_温州医科大学慈溪生物医药研究院
推荐引用方式 GB/T 7714	Liu, Shouyue,Hao, Jinkui,Xu, Yanwu,et al. Polar-Net: A Clinical-Friendly Model for Alzheimer's Disease Detection in OCTA Images[C]. CHAM:Springer Science and Business Media Deutschland GmbH,2023:607-617.