Dual-wavelength retinal image registration based on vessel segmentation and optic disc detection

doi:10.1117/12.2243587

CORC > 光电技术研究所 > 中国科学院光电技术研究所 > 自适应光学技术研究室（八室）

	Dual-wavelength retinal image registration based on vessel segmentation and optic disc detection
	Xian, Yong-Li 1,2,3,4; Dai, Yun 1,3; Gao, Chun-Ming 2; Du, Rui 1,3
刊名	Proceedings of SPIE: 8th International Symposium on Advanced Optical Manufacturing and Testing Technology: Optical Test, Measurement Technology, and Equipment
	2016
卷号	9684 页码:968417
关键词	Cameras Image Registration Information Use Manufacture Ophthalmology Optical Testing Oxygen Spectrophotometers Spectrophotometry Stereo Vision
ISSN号	0277-786X
DOI	10.1117/12.2243587
文献子类	C
英文摘要	The dual-wavelength retinal image registration is one of the critical steps in the spectrophotometric measurements of oxygen saturation in the retinal vasculature. The dual-wavelength images (570 nm and 600 nm) are simultaneously captured by dual-wavelength retinal oximeter based on commercial fundus camera. The retinal oxygen saturation is finally measured after vessel segmentation, image registration and calculation of optical density ratio of the two images. Because the dual-wavelength images are acquired from different optical path, it is necessary to go through image registration before they are used to analyze the oxygen saturation. This paper presents a new approach to dual-wavelength retinal image registration based on vessel segmentation and optic disc detection. Firstly, the multi-scale segmentation algorithm based on the Hessian matrix is used to realize vessel segmentation. Secondly, after optic disc is detected by convergence index filter and the center of the optic disc is obtained by centriod algorithm, the translational difference between the images can be determined. The center of the optic disc is used as the center of rotation, and the registration based on mutual information can be achieved using contour and gray information of vessels through segmented image. So the rotational difference between the images can be determined too. The result shows that the algorithm can provide an accurate registration for the dual-wavelength retinal image. © 2016 SPIE.
语种	英语
WOS记录号	WOS:000387429500043
资助机构	Chinese Academy of Sciences, Institute of Optics and Electronics (IOE) ; The Chinese Optical Society (COS)
内容类型	期刊论文
源URL	[http://ir.ioe.ac.cn/handle/181551/8437]
专题	光电技术研究所_自适应光学技术研究室（八室）
作者单位	1.Key Laboratory of Adaptive Optics, Chinese Academy of Sciences, Chengdu Sichuan 2.610209, China 3.School of Optoelectronic Information, University of Electronic Science and Technology of China, Chengdu, Sichuan 4.610054, China 5.Institute of Optics and Electronics, Chinese Academy of Sciences, Chengdu, Sichuan 6.610209, China 7.University of Chinese Academy of Sciences, Beijing 8.100049, China
推荐引用方式 GB/T 7714	Xian, Yong-Li,Dai, Yun,Gao, Chun-Ming,et al. Dual-wavelength retinal image registration based on vessel segmentation and optic disc detection[J]. Proceedings of SPIE: 8th International Symposium on Advanced Optical Manufacturing and Testing Technology: Optical Test, Measurement Technology, and Equipment,2016,9684:968417.
APA	Xian, Yong-Li,Dai, Yun,Gao, Chun-Ming,&Du, Rui.(2016).Dual-wavelength retinal image registration based on vessel segmentation and optic disc detection.Proceedings of SPIE: 8th International Symposium on Advanced Optical Manufacturing and Testing Technology: Optical Test, Measurement Technology, and Equipment,9684,968417.
MLA	Xian, Yong-Li,et al."Dual-wavelength retinal image registration based on vessel segmentation and optic disc detection".Proceedings of SPIE: 8th International Symposium on Advanced Optical Manufacturing and Testing Technology: Optical Test, Measurement Technology, and Equipment 9684(2016):968417.