Algorithm of Locally Adaptive Region Growing Based on Multi-Template Matching Applied to Automated Detection of Hemorrhages
GAO Wei-wei1, SHEN Jian-xin1, WANG Yu-liang1, LIANG Chun1, ZUO Jing2
1. College of Mechanical & Electrical Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China 2. Jiangsu Province Hospital of TCM, Nanjing 210029, China
Abstract：In order to automatically detect hemorrhages in fundus images, and develop an automated diabetic retinopathy screening system, a novel algorithm named locally adaptive region growing based on multi-template matching was established and studied. Firstly, spectral signature of major anatomical structures in fundus was studied, so that the right channel among RGB channels could be selected for different segmentation objects. Secondly, the fundus image was preprocessed by means of HSV brightness correction and contrast limited adaptive histogram equalization(CLAHE). Then, seeds of region growing were founded out by removing optic disc and vessel from the resulting image of normalized cross-correlation(NCC)template matching on the previous preprocessed image with several templates. Finally, locally adaptive region growing segmentation was used to find out the exact contours of hemorrhages, and the automated detection of the lesions was accomplished. The approach was tested on 90 different resolution fundus images with variable color, brightness and quality. Results suggest that the approach could fast and effectively detect hemorrhages in fundus images, and it is stable and robust. As a result, the approach can meet the clinical demands.
[1] PU Yi-min, YANG Jun, YANG Tian(蒲一民, 杨 君, 杨 田). Int. J. Ophthalmol.(国际眼科杂志), 2011, 11(12): 2134. [2] Watkins P J. British Medical Journal, 2003, 7(2): 105. [3] Sanchez C I, Hornero R, Lopez M I, et al. 26th IEEE Annual International Conference on Engineering in Medicine and Biology Society, San Francisco, CA, USA: EMBC, 2004, 1: 1624. [4] Villarroel M, Ciudin A, Hernndez C, et al. World J Diabetes, 2010, 1(2): 57. [5] PENG Jin-juan, ZOU Hai-dong, WANG Wei-wei, et al(彭金娟, 邹海东, 王伟伟, 等). Chinese Journal of Ophthalmology(中华眼科杂志), 2010, 46(3): 258. [6] ZHANG Lei, XU Wei-qiang, TAN Rong-qiang, et al(张 蕾, 许维强, 谭荣强, 等). Int. J. Ophthalmol(国际眼科杂志), 2010, 10(3): 482. [7] CHEN Zhe, ZHANG Shi-sheng, ZHU Hui-min(陈 喆, 张士胜, 朱惠敏). Int. J. Ophthalmol(国际眼科杂志), 2011, 11(8): 1394. [8] Sinthanayothin C, Boyce J F, Williamson T H, et al. Diabetic Medicine, 2002, 19(2): 105. [9] Meindert Niemeijer, Bram van Ginneken, Stephen R. Russell, et al. Investigative Ophthalmology & Visual Science, 2007, 48(5): 2260. [10] LIN Wei(林 蔚). Shanghai Jiaotong University(上海交通大学), 2008. [11] GAO Wei-wei, SHEN Jian-xin, WANG Yu-liang(高玮玮, 沈建新, 王玉亮). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2012, 32(4): 760. [12] Usher D, Dumskyj M, Himaga M, et al. Diabetic UK Diabetic Medicine, 2004, 21(1): 84. [13] Niemeijer M, van Ginneken B, Staal J, et al. IEEE Trans. Med. Imaging, 2005, 24(5): 584. [14] Yuji Hatanaka, Toshiaki Nakagawa, Yoshinori Hayashi, et al. 30th Annual International IEEE EMBS Conference, Vancouver, British Columbia, Canada, 2008. 5429. [15] Dupas B, Walter T, Erginay A, et al. Diabetes & Metabolism, 2010, 36(3): 213. [16] Chihara E, Matsuoka T, Ogura Y, et al. Ophthalmology, 1993, 100: 1147. [17] QU Jia, YAN Zong-hui, Lü Fan, et al(瞿 佳, 严宗辉, 吕 帆, 等). Chinese Journal of Ophthalmology(中华眼科杂志), 1995, 31(6): 417. [18] Adams R, Bischof L. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1994, 16(6): 641. [19] Rosenman J, Roe C A，Cromartie R, et al. Int. J. Rdaiat. Oncol. Biol. Physics, 1993, 333. [20] WEI Wu, HUANG Xin-han, ZHANG Qi-sen, et al(魏 武, 黄心汉, 张起森, 等). PR&AI(模式识别与人工智能), 2001, 14(1): 123. [21] Javitt J C, Canner J K, Frank R G, et al. Ophthalmology, 1990, 97(4): 483.
