基于投影的视网膜眼底图像视盘检测方法

doi:10.3969/j.issn.0258-8021. 2013. 04.014

摘要
图/表
参考文献
相关文章 (6)

全文: PDF (716 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要充分利用血管的分布特性和视盘区域的外观特性，本研究提出一种易于实现的基于一维投影的视盘检测方法。首先利用2倍主血管宽度的垂直窗计算各水平位置的血管散布度值，并绘出相应的水平投影曲线，投影曲线的最小值点被确定为视盘的水平坐标，然后在确定的水平位置，通过边长为视盘直径的矩形窗获取局部区域内的亮度和血管边缘梯度特征，并绘出相应的垂直投影曲线，该曲线最大值点即为视盘垂直坐标。将本方法在4个公开的眼底图像数据集和1个自选数据集上进行了测试，在整个380幅眼底图像中，检测准确率达到94%，在STARE数据库中平均用时13.2 s，综合准确率和效率来看，本方法易于实现，鲁棒性好，符合实际系统处理要求。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章

关键词 ：视盘检测, 投影, 视网膜图像

Abstract：In order to utilize the vessel distribution and optic disc (OD) appearance characteristics effectively, a novel OD localization method based on 1-D projection was proposed in this work. First, vertical windows with 2 main vessel widths were used to compute the vascular scatter degree of every horizontal position, and corresponding horizontal projection curve was plotted, the horizontal location of OD was identified as the location of the minimum position of the horizontal projection curve. Next, a rectangular window slid up to down at determined horizontal location to obtain the brightness and edge gradient features of local regions, and corresponding vertical projection curve was plotted. The maximum peak of the vertical projection curve was set as the vertical position of OD. The proposed method was tested with four publiclyavailable databases and a selfselection database. The OD was successfully located in 357 images out of 380 images (94%). And the average time for one image in STARE dataset was 13.2 s. Regarding to accuracy and efficiency, the proposed method was easy to implement and present good robust performance.

Key words： optic disc detection projection retinal image

基金资助:湖南省教育厅资助科研项目(10B109)；湖南省科技厅资助项目（2012FJ3113）；湖南省重点学科资助

引用本文:

张东波^1,2*易瑶¹赵圆圆^{1. 基于投影的视网膜眼底图像视盘检测方法[J]. 中国生物医学工程学报, 2013, 32(4): 477-483.

ZHANG Dong Bo^{1, 2,*}YI Yao¹ ZHAO Yuan Yuan ^1. Projection Based Optic Disk Detection Method in Retinal Fundus Image. journal1, 2013, 32(4): 477-483.}

链接本文:

http://cjbme.csbme.org/CN/10.3969/j.issn.0258-8021. 2013. 04.014 或 http://cjbme.csbme.org/CN/Y2013/V32/I4/477

［1］Sinthanayothin C, Boyce JF, Cook HL, et al. Automated location of the optic disk, fovea, and retinal blood vessels from digital color fundus images［J］. Br J Ophthalmol, 1999, 83(8):902-910.
［2］Li Huiqi, Chutatape O. Automatic location of optic disk in retinal images［C］ //IEEE International Conference on Image Processing. Thessaloniki: IEEE, 2001, 2:837-840. 
［3］Li Huiqi, Chutatape O. Automatic feature extraction in color retinal images by a model based approach［J］. IEEE Trans on Biomed Eng, 2004, 51(2):246-254.
［4］Barrett SF, Naess E, Molvik T. Employing the Hough transform to locate the optic disk ［J］. Biomed Sci Instrum, 2001, 37(1):81-86.
［5］Haar FT. Automatic localization of the optic disc in digital colour images of the human retina ［D］. Utrecht: Utrecht University, 2005.
［6］Foracchia M, Grisan E, Ruggeri A. Detection of optic disc in retinal images by means of a geometrical model of vessel structure ［J］. IEEE Trans Med Imaging, 2004, 23(10):1189-1195.
［7］Hoover GA, Goldbaum M. Locating the optic nerve in a retinal image using the fuzzy convergence of the blood vessels ［J］. IEEE Trans Med Imaging, 2003, 22(8):951-958.
［8］Youssif A, Ghalwash A, Ghoneim A. Optic disc detection from normalized digital fundus images by means of a vessels’ direction matched filter ［J］. IEEE Trans Med Imaging, 2008, 27(1):11-18.
［9］Mahfouz AE, Fahmy AS. Fast localization of the optic disc using projection of image feature ［J］. IEEE Trans Image Proc, 2010, 19(12):3285-3289.
［10］Goldbaum M, Moezzi S, Taylor A, et al. Automated diagnosis and image understanding with object extraction, object classification, and inferencing in retinal images ［C］ //IEEE International Conference on Image Processing. Los Alamitos: IEEE, 1996, 3:695-698.
［11］Lowell J, Hunter A, Steel D, et al. Optic nerve head segmentation ［J］. IEEE Trans Med Imaging, 2004, 23(2):256-264.
［12］Tobin KW, Chaum E, Govindasamy VP, et al. Characterization of the optic disc in retinal imagery using a probabilistic approach ［C］ //Proc SPIE Med Imaging. San Diego: SPIE, 2006, 6144:1088-1097.
［13］Abràmoff MD, Niemeijer M. The automatic detection of the optic disc location in retinal images using optic disc location regression［C］ //IEEE International ConferenceEMBS. New York: IEEE, 2006: 4432-4435.
［14］张东波，尚星宇. 病变视网膜图像的血管骨架提取方法研究［J］.电子测量与仪器学报，2011, 25(9):749-755.
［15］Walter T, Klein JC. Segmentation of color fundus images of the human retina: Detection of the optic disc and the vascular tree using morphological techniques ［C］ //Crespo J, eds. Int Symp Med Data Anal. Berling: SpringerVerlag, 2001: 282-287.
［16］Osareh A. Automated identification of diabetic retinal exudates and the optic disc［D］. Bristol: University of Bristol, 2004.
［17］Lalonde M, Beaulieu M, Gagnon L. Fast and robust optic disk detection using pyramidal decomposition and Hausdorffbased template matching ［J］. IEEE Trans Med Imaging, 2001, 20(11):1193-1200.
［18］Tasman W, Jaeger E A. Duane’s Ophthalmology ［M］. (15th Edition). Philadelphia: Lippincott Williams & Wilkins, 2009.