A simple hybrid method for segmenting vessel structures in retinal fundus images

In this paper, a simple, fast, and efficient hybrid segmentation method is presented for extracting vessel structures in retinal fundus images. Basically, this hybrid approach combines circular and naive Bayes classifiers to extract blood vessels in retinal fundus images. The circular method samples pixels along the enlarging circles centered at the current pixel and classifies the current pixel as vessel or nonvessel. An elimination technique is then employed to eliminate the nonvessel fragments from the processed image. The naive Bayes method as a supervised technique uses a very small set of features to segment retinal vessels in retinal images. The designed hybrid method exploits the circular and Bayesian segmentation results together to achieve the best performance. The achieved performance of the segmentation methods are tested on DRIVE and STARE databases for evaluation. The proposed methods segment a retinal image within 1 s and achieve about 95% accuracy. The results also indicate that the proposed hybrid method is one of the simplest and efficient segmentation methods among the unsupervised and supervised methods in the literature.

PDF

___

[1] K¨ose C, ˙Ikiba¸s C. A personal identification system using retinal vasculature in retinal fundus images. Expert Syst Appl 2011; 38: 1367013681.
[2] Lowell JA, Hunter A, Steel D, Basu A, Ryder R, Kennedy RL. Measurement of retinal vessel widths from fundus images based on 2-D modeling. IEEE T Med Imaging 2004; 23: 11961204.
[3] K¨ose C, S¸evik U, ˙Ikiba¸s C, Erd¨ol H. Simple methods for segmentation and measurement of diabetic retinopathy lesions in retinal fundus images. Comput Meth Prog Bio 2011; 107: 274293.
[4] Gang L, Chutatape O, Krishnan SM. Detection and measurement of retinal vessels in fundus images using amplitude modified second-order Gaussian filter. IEEE T Bio-Med Eng 2002; 49: 168172.
[5] Kayık¸cıo˘glu T, Gangal A, Turhal M, K¨ose C. A surface-based method for detection of coronary vessel boundaries in poor quality X-ray angiogram images. Pattern Recogn Lett 2002; 23: 783802.
[6] Yavuz Z, ˙Ikiba¸s C, K¨ose C. A simple analytic approach for tracking retinal vessel and measuring their diameters. In: International Conference on Bioinformatics; 2023 January 2010; Valencia, Spain.
[7] Cosatto VF, Liew G, Rochtchina E, Wainwright A, Zhang Y, Hsu W, Lee ML, Lau QP, Hamzah HH, Mitchell P et al. Retinal vascular fractal dimension measurement and its influence from imaging variation: results of two segmentation methods. Curr Eye Res 2010; 35: 850856.
[8] Zhou H, Schaefer G, Liu T, Lin F. Segmentation of optic disc in retinal images using an improved gradient vector flow algorithm. Multimed Tools Appl 2010; 49: 447462.
[9] Mendon¸ca AM, Campilho A. Segmentation of retinal blood vessels by combining the detection of centerlines and morphological reconstruction. IEEE T Med Imaging 2006; 25: 12001213.
[10] Marwan DS, Eswaran C, Mueen A. An automated blood vessel segmentation algorithm using histogram equalization and automatic threshold selection. J Digit Imaging 2011; 24: 564572.
[11] Zhang Y, Hsu W, Lee ML. Segmentation of retinal vessels using nonlinear projections. In: IEEE International Conference on Image Processing; 1619 September 2007; San Antonio, TX, USA. New York, NY, USA: IEEE. pp.541544.
[12] Bhuiyan A, Nath B, Chua J, Kotagiri R. Blood vessel segmentation from color retinal images using unsupervised texture classification. In: IEEE International Conference on Image Processing; 1619 September 2007; San Antonio, TX, USA. New York, NY, USA: IEEE. pp. 521524.
[13] Ricci E, Perfetti R. Retinal blood vessel segmentation using line operators and support vector classification. IEEE T Med Imaging 2007; 26: 13571365.
[14] Vermeer KA, Vos FM, Lemij HG, Vossepoel AM. A model based method for retinal blood vessel detection. Comput Biol Med 2004; 34: 209219.
[15] Ghaderi R, Hassanpour H, Shahiri M. Retinal vessel segmentation using the 2-D Morlet wavelet and neural network. In: International Conference on Intelligent and Advanced Systems; 2528 November 2007; Kuala Lumpur, Malaysia. New York, NY, USA: IEEE. pp. 12511255.
[16] Perfetti R, Ricci E, Casali D, Costantini G. Cellular neural networks with virtual template expansion for retinal vessel segmentation. IEEE T Circuits-II 2007; 54: 141145.
[17] Chutatape O, Zheng L, Krishman S. Retinal blood vessel detection and tracking by matched Gaussian and Kalman filters. In: Proceedings of the 20th Annual International Conference of the IEEE Engineering in Medicine and Biology Society; 1998; Hong Kong. New York, NY, USA: IEEE. pp. 31443149.
[18] Mar´ın D, Aquino A, Geg´undez-Arias ME, Bravo JM. A new supervised method for blood vessel segmentation in retinal images by using gray-level and moment invariants-based features. IEEE T Med Imaging 2011; 30: 146158.
[19] Niemeijer M, Staal J, van Ginneken B, Loog M, Abr`amoff MD. Comparative study of retinal vessel segmentation methods on a new publicly available database. SPIE Med Imag 2004; 5370: 648656.
[20] K¨ose C, ˙Ikiba¸s C. Segmentation of coronary vessel structures in X-ray angiogram images by using spatial pattern matching method. In: 23rd International Symposium on Computer and Information Sciences; 2729 October 2009; ˙Istanbul, Turkey. New York, NY, USA: IEEE. pp. 16.
[21] Zana F, Klein JC. Segmentation of vessel-like patterns using mathematical morphology and curvature evaluation. IEEE T Image Process 2001; 10: 10101019.
[22] Hoover A, Kouznetsova V, Goldbaum M. Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response. IEEE T Med Imaging 2000; 19: 203210.
[23] Staal J, Abramoff MD, Niemeijer M, Viergever MA, Ginneken BV. Ridge-based vessel segmentation in color images of the retina. IEEE T Med Imaging 2004; 23: 501509.
[24] Soares JVB, Leandro JJG, Cesar RM Jr, Jelinek HF, Cree MJ. Retinal vessel segmentation using the 2-D Gabor wavelet and supervised classification. IEEE T Med Imaging 2006; 25: 12141222.
[25] Mar´ın D, Aquino A, Geg´undez-Arias ME, Bravo JM. A new supervised method for blood vessel segmentation in retinal images by using gray-level and moment invariants-based features. IEEE T Med Imaging 2011; 30: 146158.
[26] You X, Peng Q, Yuan Y, Cheung Y, Lei J. Segmentation of retinal blood vessels using the radial projection and semi-supervised approach. Pattern Recogn 2011; 44: 23142324.
[27] Jiang X, Mojon D. Adaptive local thresholding by verification-based multithreshold probing with application to vessel detection in retinal images. IEEE T Pattern Anal 2003; 25: 131137.
[28] Lam BSY, Yan H. A novel vessel segmentation algorithm for pathological retina images based on the divergence of vector fields. IEEE T Med Imaging 2008; 27: 237246.
[29] Chaudhuri S, Chatterjee S, Katz N, Nelson M, Goldbaum M. Detection of blood vessels in retinal images using two-dimensional matched filters. IEEE T Med Imaging 1989; 8: 263269.
[30] Rogers DF. Procedural Elements for Computer Graphics. New York, NY, USA: McGraw-Hill, 1988.
[31] Duda RO, Hart PE, Stork DG. Pattern Classification. Chichester, UK: John Wiley & Sons, 2001.
[32] Peng F, Schuurmans D. Combining naive Bayes and n-gram language models for text classification. Lect Notes Comp Sci 2003; 2633: 335350.