基于定向局部对比度的眼底图像视盘检测方法

doi:10.3969/j.issn.0258-8021. 2014. 03.05

摘要
图/表
参考文献
相关文章 (6)

全文: PDF (2179 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要视盘作为眼底图像的一个重要特征，其自动检测方法在眼底病变图像分析中有着重要的作用。提出一种基于定向局部对比度滤波的方法，有效地提取眼底图像中的局部亮度区域；结合视盘区域的局部血管特征，选择定位出正确的视盘感兴趣区域；采用数学形态学方法和区域主动轮廓模型，可较准确地检测出视盘轮廓。对开放的STARE数据库上的81幅眼底图像进行测试，其中含31幅正常和50幅病变图像（含严重病理图像），用该方法正确检测出视盘73幅，准确率约为90.1%。结果表明，该方法有效地克服大块亮斑病灶对视盘检测的影响，且仅需提取粗血管，计算较为简单，说明了算法的有效性。

	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
	郑绍华^*陈健潘林余轮

关键词 ：视盘检测, 眼底图像, 定向局部对比度, 数学形态学, 区域主动轮廓模型

Abstract：The optic disc (OD) is considered as one of the main features of a retinal image. OD detection is a main step in developing automated analysis systems for the retinopathy. In this paper, we proposed a method aiming to effectively extract the local brightness areas in digital retinal fundus images based on directional local contrast (DLC) filter. The right OD region of interest (ROI) was selected by considering its local vessels features. Thereupon, in the selected ROI, the OD contour was exactly detected using the mathematical morphology method and regionbased active contour model technique. The evaluation for the proposed method was performed using the dataset of 81 images from the public STARE project, containing images from both normal (31) and pathological (50) subjects, even including severe pathological situations. The OD position was correctly identified in 73 out of 81 images, the accuracy rate is about 90.1%. These results demonstrate that the method effectively overcomes the influence from the large bright spot lesions on OD detection by just extracting the large vessels and less computation time.

Key words： optic disc detection retinal image directional local contrast mathematical morphology regionbased active contour model

基金资助:国家自然科学基金（60827002）；福建省教育厅项目（JA13037）

引用本文:

郑绍华^*陈健潘林余轮. 基于定向局部对比度的眼底图像视盘检测方法[J]. 中国生物医学工程学报, 2014, 33(3): 289-296.
ZHENG Shao Hua^* CHEN Jian PAN Lin YU Lun. Optic Disc Detection on Retinal Images Based on Directional Local Contrast. journal1, 2014, 33(3): 289-296.

链接本文:

http://cjbme.csbme.org/CN/10.3969/j.issn.0258-8021. 2014. 03.05 或 http://cjbme.csbme.org/CN/Y2014/V33/I3/289

［1］AbdelRazik Youssif AAH, Ghalwash AZ, AbdelRahman Ghoneim AAS. 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.
［2］朱琳琳, 唐延东. 基于眼底特征的视盘自动检测［J］. 仪器仪表学报, 2010, 31(8): 118-122.
［3］Qureshi RJ, Kovacs L, Harangi B, et al. Combining algorithms for automatic detection of optic disc and macula in fundus images ［J］. Computer Vision and Image Understanding, 2012, 116(1): 138-145.
［4］Sinthanayothin C, Boyce JF, Cook HL, et al. Automated localisation of the optic disc, fovea, and retinal blood vessels from digital colour fundus images ［J］. British Journal of Ophthalmology, 1999, 83(8): 902-910.
［5］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 ［M］ //Medical Data Analysis. BerLin: Springer Berlin Heidelberg, 2001: 282-287.
［6］Li Huihua, Chutatape O. Automatic location of optic disk in retinal images ［C］ //Proceedings of International Conference on Image Processing. Thessaloniki: IEEE, 2001, 2: 837-840. 
［7］Lalonde M, Beaulieu M, Gagnon L. Fast and robust optic disc detection using pyramidal decomposition and Hausdorffbased template matching ［J］. IEEE Trans Med Imaging, 2001, 20(11): 1193-1200.
［8］Hoover A, 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.
［9］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.
［10］Niemeijer M, Abràmoff MD, van Ginneken B. Fast detection of the optic disc and fovea in color fundus photographs ［J］. Medical image analysis, 2009, 13(6): 859-870.
［11］Welfer D, Scharcanski J, Kitamura CM, et al. Segmentation of the optic disk in color eye fundus images using an adaptive morphological approach ［J］. Computers in Biology and Medicine, 2010, 40(2): 124-137.
［12］Goldbaum M. The STARE (STructured Analysis of the Retina) Project ［DB/OL］. http://www.parl.clemson.edu/～ahoover/stare, 2013-01/2013-09-24. 
［13］Zhang Ming, Liu J C. Directional local contrast based blood vessel detection in retinal images ［C］ //IEEE International Conference on Image Processing. San Antonio: IEEE, 2007, 4: IV-317-IV-320. 
［14］Otsu N. A threshold selection method from gray level histograms ［J］. IEEE Transactions on Systems, Man, and Cybernetics, 1979, SMC-9(1): 62-66.
［15］Fleming AD, Philip S, Goatman KA, et al. Automated microaneurysm detection using local contrast normalization and local vessel detection ［J］. IEEE Trans Med Imaging, 2006, 25(9): 1223-1232.
［16］Chan TF, Vese LA. Active contours without edges ［J］. IEEE Transactions on Image Processing, 2001, 10(2): 266-277.
［17］Osareh A, Mirmehdi M, Thomas B, et al. Comparison of colour spaces for optic disc localisation in retinal images ［C］ //Proceedings of 16th International Conference on Pattern Recognition. Quebec: IEEE, 2002, 1: 743-746. 
［18］ter Haar F. Automatic localization of the optic disc in digital colour images of the human retina ［D］. Utrecht: Utrecht University, 2005. 
［19］夏伟, 王利, 李蓬秋, 等. 应用免散瞳眼底照相技术筛查糖尿病视网膜病变临床分析［J］. 国际眼科杂志(中文刊), 2013, 13(11): 2267-2269.
［20］B. van Ginneken. The DRIVE (Digital Retinal Images for Vessel Extraction) database ［DB/OL］. http://www.isi.uu.nl/Research/ Databases/DRIVE, 2007-04/2013-09-24.