AUTOMATIC BLOOD VESSEL SEGMENTATION IN COLOR IMAGES OF RETINA

Automated image processing techniques have the ability to assist in the early detection of diabetic retinopathy disease which can be regarded as a manifestation of diabetes on the retina. Blood vessel segmentation is the basic foundation while developing retinal screening systems, since vessels serve as one of the main retinal landmark features. This paper proposes an automated method for identification of blood vessels in color images of the retina. For every image pixel, a feature vector is computed that utilizes properties of scale and orientation selective Gabor filters. The extracted features are then classified using generative Gaussian mixture model and discriminative support vector machines classifiers. Experimental results demonstrate that the area under the receiver operating characteristic (ROC) curve reached a value 0.974, which is highly comparable and, to some extent, higher than the previously reported ROCs that range from 0.787 to 0.961. Moreover, this method gives a sensitivity of 96.50% with a specificity of 97.10% for identification of blood vessels. Keywords– Retinal blood vessels, Gabor filters, support vector machines, vessel segmentation

[1]  Shigeo Abe DrEng.  Pattern Classification , 2001, Springer London.

[2]  Esther de Ves,et al.  Segmentation of macular fluorescein angiographies. A statistical approach , 2001, Pattern Recognit..

[3]  J. Rissanen.  A UNIVERSAL PRIOR FOR INTEGERS AND ESTIMATION BY MINIMUM DESCRIPTION LENGTH , 1983 .

[4]  Xiaoyi Jiang,et al.  Adaptive Local Thresholding by Verification-Based Multithreshold Probing with Application to Vessel Detection in Retinal Images , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  C. Metz.  ROC Methodology in Radiologic Imaging , 1986, Investigative radiology.

[6]  Martin A. Fischler,et al.  Detection of roads and linear structures in low-resolution aerial imagery using a multisource knowledge integration technique☆ , 1981 .

[7]  Max A. Viergever,et al.  Ridge-based vessel segmentation in color images of the retina , 2004, IEEE Transactions on Medical Imaging.

[8]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[9]  H Rabani,et al.  WAVELET BASED IMAGE DENOISING BASED ON A MIXTURE OF LAPLACE DISTRIBUTIONS , 2006 .

[10]  A. Pinz,et al.  Mapping the human retina , 1996, IEEE Transactions on Medical Imaging.

[11]  Oscar Nestares,et al.  Efficient spatial-domain implementation of a multiscale image representation based on Gabor functions , 1998, J. Electronic Imaging.

[12]  Christopher J. Taylor,et al.  Detection of non-perfused zones in retinal images , 1991, [1991] Computer-Based Medical Systems@m_Proceedings of the Fourth Annual IEEE Symposium.

[13]  Herbert F. Jelinek,et al.  Comparison of various methods to delineate blood vessels in retinal images , 2005 .

[14]  Ying Sun,et al.  Back-propagation network and its configuration for blood vessel detection in angiograms , 1995, IEEE Trans. Neural Networks.

[15]  Frédéric Zana,et al.  A multimodal registration algorithm of eye fundus images using vessels detection and Hough transform , 1999, IEEE Transactions on Medical Imaging.

[16]  Roberto Marcondes Cesar Junior,et al.  Retinal vessel segmentation using the 2-D Gabor wavelet and supervised classification , 2005, IEEE Transactions on Medical Imaging.

[17]  Bram van Ginneken,et al.  Comparative study of retinal vessel segmentation methods on a new publicly available database , 2004, SPIE Medical Imaging.

[18]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[19]  D. DeMets,et al.  The Wisconsin epidemiologic study of diabetic retinopathy. II. Prevalence and risk of diabetic retinopathy when age at diagnosis is less than 30 years. , 1984, Archives of ophthalmology.

[20]  M. Goldbaum,et al.  Detection of blood vessels in retinal images using two-dimensional matched filters. , 1989, IEEE transactions on medical imaging.

[21]  Shinichi Tamura,et al.  Zero-crossing interval correction in tracing eye-fundus blood vessels , 1988, Pattern Recognit..

[22]  Paul F. Whelan,et al.  Experiments in colour texture analysis , 2001, Pattern Recognit. Lett..

[23]  Roberto Marcondes Cesar Junior,et al.  Blood vessels segmentation in retina: preliminary assessment of the mathematical morphology and of the wavelet transform techniques , 2001, Proceedings XIV Brazilian Symposium on Computer Graphics and Image Processing.

[24]  David G. Stork,et al.  Pattern Classification , 1973 .

[25]  E. Gregersen,et al.  [Early photocoagulation of diabetic retinopathy]. , 1981, Ugeskrift for laeger.

[26]  Ian T. Nabney,et al.  Netlab: Algorithms for Pattern Recognition , 2002 .

[27]  Yannis A. Tolias,et al.  A fuzzy vessel tracking algorithm for retinal images based on fuzzy clustering , 1998, IEEE Transactions on Medical Imaging.

[28]  S. Sangwine,et al.  The Colour Image Processing Handbook , 1998, Springer US.

[29]  A.D. Hoover,et al.  Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response , 2000, IEEE Transactions on Medical Imaging.

[30]  Bernt Schiele,et al.  Recognition without Correspondence using Multidimensional Receptive Field Histograms , 2004, International Journal of Computer Vision.

[31]  Frédéric Zana,et al.  Segmentation of vessel-like patterns using mathematical morphology and curvature evaluation , 2001, IEEE Trans. Image Process..

[32]  Mohammed Al-Rawi,et al.  Genetic algorithm matched filter optimization for automated detection of blood vessels from digital retinal images , 2007, Comput. Methods Programs Biomed..

[33]  Shinichi Tamura,et al.  Semiautomatic leakage analyzing system for time series fluorescein ocular fundus angiography , 1983, Pattern Recognit..

[34]  M Gyllenberg,et al.  A fragment library based on Gaussian mixtures predicting favorable molecular interactions. , 2001, Journal of molecular biology.

[35]  H. RABBANI,et al.  WAVELET BASED IMAGE DENOISING BASED ON A MIXTURE OF LAPLACE DISTRIBUTIONS , 2007 .