Automatic localization and segmentation of optic disk in color fundus image

被引：7

作者：

Zou, Bei-Ji ^{[1
,2
]}

Zhang, Si-Jian ^{[1
,2
]}

Zhu, Cheng-Zhang ^{[1
,2
,3
]}

机构：

[1] School of Information Science and Engineering, Central Sounth University, Changsha

[2] “Mobile Health” for Ministry of Education-China Mobile Joint Laboratory, Changsha

[3] Hunan Institute of Science and Technology, Yueyang

来源：

Guangxue Jingmi Gongcheng/Optics and Precision Engineering | 2015年 / 23卷 / 04期

关键词：

Color fundus image; Image preprocessing; Optic disk localization; Optic disk segmentation;

D O I：

10.3788/OPE.20152304.1187

中图分类号：

学科分类号：

摘要：

An effective pre-processing method is proposed to overcome the influence of a bright ring caused by the edge of a color fundus image on optic disk localization. Then, a novel method integrating the morphology, ellipse fitting and a Gradient Vector Flow (GVF) Snake model is proposed to implement the segmentation of the optic disk. The proposed pre-processing method uses least square method to fit the edge of color fundus image, and then clips some bright pixels near the edge. Finally, it localizes the optic disk. Furthermore, the proposed segmentation algorithm segments the optic disk by 3 steps: vascular erase, ellipse fitting and a fine tune step using GVF Snake model. A test is performed with 1 200 color fundus images from Messidor color fundus image database. The test results indicate that the localization accuracy for the optic disk rises from 95.4% to 98.7% as comparing with the traditional method. Moreover, the optic disk segmentation error has dropped from 12.5% to 9.39% as comparing with the current known best algorithm. It concludes that the proposed method of automatic localization and segmentation of optic disk in color fundus images have strong practicability and high accuracy and are suitable for the computer-aided diagnosis of ocular diseases. ©, 2015, Chinese Academy of Sciences. All right reserved.

引用

页码：1187 / 1195

页数：8

共 22 条

[1]

Zhu C.Z., Xiang Y., Zou B.J., Et al., Retinal vessel segmentation in fundus images using CART and AdaBoost, Journal of Computer-Aided Design & Computer Graphics, 26, 3, pp. 445-451, (2014)

[2]

Xiang Y., Gao X., Zou B.J., Et al., Segmentation of retinal blood vessels based on divergence and bot-hat transform, Proceedings of International Conference on Progress in Informatics and Computing, pp. 316-320, (2014)

[3]

Quigley H.A., Broman A.T., The number of people with glaucoma worldwide in 2010 and 2020, British Journal of Ophthalmology, 90, 3, pp. 262-267, (2006)

[4]

Hoover A., Goldbaum M., Locating the optic nerve in a retinal image using the fuzzy convergence of the blood vessels, IEEE Transactions on Medical Imaging, 22, 8, pp. 951-958, (2003)

[5]

Li H.Q., Chutatape O., Automated feature extraction in color retinal images by a model based approach, IEEE Transactions on Bio-Medical Engineering, 51, 6, pp. 246-254, (2004)

[6]

Osareh A., Mirmehdi M., Thomas B., Et al., Automated identification of diabetic retinal exudates in digital colour images, British Journal of Ophthalmology, 87, 10, pp. 1220-1223, (2003)

[7]

Abdel-Razik Youssif A.A.H., Ghalwash A.Z., Abdel-Rahman Ghoneim A.A.S., Optic disc detection from normalized digital fundus images by means of a vessels' direction matched filter, IEEE Transactions on Medical Imaging, 27, 1, pp. 11-18, (2008)

[8]

Li H., Chutatape O., Automatic location of optic disk in retinal images, Proceedings of 2001 International Conference on Image Processing, pp. 837-840, (2001)

[9]

Foracchia M., Grisan E., Ruggeri A., Detection of optic disc in retinal images by means of a geometrical model of vessel structure, IEEE Transactions on Medical Imaging, 23, 10, pp. 1189-1195, (2004)

[10]

Mahfouz A.E., Fahmy A.S., Fast localization of the optic disc using projection of image features, IEEE Transactions on Image Processing, 19, 12, pp. 3285-3289, (2010)

← 1 2 3 →