Detection of hard exudates using mean shift and normalized cut method

• Autorzy: Banerjee S. , Kayal D.

Identyfikatory

DOI

10.1016/j.bbe.2016.07.001

• Języki publikacji: EN

Abstrakty

EN

As diabetic retinopathy (DR) is one of the main causes of loss of vision among diabetic patients, an early detection using automated detection techniques can prevent blindness among diabetic patients. Hard exudates constitute one of the early symptoms of DR and this paper describes a method for its detection using fundus images of retina, employing a combination of morphological operations, mean shift (MS), normalized cut (NC) and Canny's operation. This combined technique avoids over segmentation and at the same time reduces the time complexity while clearly delineating the exudates. Output of the proposed method is evaluated using public databases and produces sensitivity, specificity and accuracy as 98.80%, 98.25% and 98.65%, respectively. The ROC curve gives 0.984 as area under curve. The sensitivity, specificity, accuracy and area under curve of ROC indicate the effectiveness of the method.

Słowa kluczowe

EN

mean shift; normalized cut; image segmentation; retina; hard exudates

PL

cięcie znormalizowane; segmentacja obrazu; siatkówka oka; wysięk twardy

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2016
• Tom: Vol. 36, no. 4
• Strony: 679--685
• Opis fizyczny: Bibliogr. 29 poz., rys., tab.

Twórcy

autor

Banerjee S.

• School of Computer Science & Engineering, West Bengal University of Technology, Kolkata, India

autor

Kayal D.

• School of Computer Science & Engineering, West Bengal University of Technology, Kolkata, India

Bibliografia

• [1] Khan MW. Diabetic retinopathy using image processing: a survey. Int J Emerg Technol Res 2013;1(1):16–20.
• [2] Fraz MM, Remagnino P, Hoppe A, Uyyanonvara B, Rudnicka AR, Owen CG, et al. Blood vessel segmentation methodologies in retinal images: a survey. Comput Methods Programs Biomed 2012;108(1):407–33.
• [3] Sopharak A, Uyyanonvara B, Barman S, Williamson S. Automatic detection of diabetic retinopathy from non-dilated retinal images using mathematical morphology methods. Comput Med Imaging Graph 2008;32:720–7.
• [4] Sopharak A, Uyyanonvara B, Barman S. Automatic exudate detection of from non-dilated diabetic retinopathy retinal images using fuzzy c-means clustering. Sensors 2009;9 (3):2148–61.
• [5] Kaur J, Mittal D. Segmentation and measurement of exudates in fundus images of retina for detection of retinal disease. J Biomed Eng Med Imaging 2015;2(1):28–38.
• [6] Kayal D, Banerjee S. A method to detect hard exudates using normalized cut image segmentation technique in digital retinal fundus image. Adv Intell Soft Comput 2012;166:123–8.
• [7] Elbalaoui A, Fakir M, Merbouha A. Segmentation and detection of diabetic retinopathy exudates. Int J Comput Appl 2014;91(6):7–13.
• [8] Osareh A, Shadgar B, Markham R. A computational intelligence based approach for detection of exudates in diabetic retinopathy. IEEE Trans Inf Technol Biomed 2009;13 (4):535–45.
• [9] Shi J, Malik J. Normalized cuts and image segmentation. IEEE Trans Pattern Anal Mach Intell 2000;22(8):888–905.
• [10] Sáez A, Serrano C, Acha B. Normalized cut optimization based on color perception findings: a comparative study. Mach Vis Appl 2014;25:1813–23.
• [11] Comaniciu D, Meer P. Mean shift: a robust approach toward feature space analysis. IEEE Trans Pattern Anal Mach Intell 2002;603–26.
• [12] Dang Ba Khac T, Maruyama T. Real-time color image segmentation based on mean shift algorithm using an FPGA. J Real Time Image Proc 2015;10:345–56.
• [13] Tao W, Jin H. Color image segmentation based on mean shift and normalized cut. IEEE Trans Syst Man Cybern 2007;37(8):1382–9.
• [14] Canny J. A computational approach to edge detection. IEEE Trans Pattern Anal Mach Intell 1986;8(6):679–98.
• [15] Walter T, Klein JC, Massin P, Erginay A. A contribution of image processing to the diagnosis of diabetic retinopathy – detection of exudates in color fundus image of human retina. IEEE Trans Med Imaging 2002;21(October (10)):256–64.
• [16] Sagar AV, Balasubramaniam B, Chandrasekhara V. A novel integrated approach using dynamic thresholding and edge detection for automatic detection of exudates in digital fundus retinal images. IEEE International Conference on Computing. 2007. pp. 286–92.
• [17] Li H, Chutatape O. A model based approach for automated feature extraction in fundus images. IEEE International Conference on Computer Vision. 2003. pp. 127–33.
• [18] Welfer D, Scharcanski J, Marinho DR. A coarse-to fine strategy for automatically detecting exudates in color eye fundus images. Comput Med Imaging Graph 2010;34(3): 228–35.
• [19] Garcia M, Sanchez CI, Lopez MI, Absolo D, Hornero R. Neural network based detection of hard exudates in retinal images. Comput Methods Programs Biomed 2009;93(1):9–19.
• [20] Niemeijer M, Van Ginneken B, Stephen R, suttorp-Schulten MSA, Abràmoff MD. Automated detection and differentiation of drusen, exudates, and cotton-wool spots in digital color fundus photographs for diabetic retinopathy diagnosis. Invest Ophthalmol Vis Sci 2007;48(5):260–2267.
• [21] Jian Z, Lu P-R, Xiang D, Dai Y-K, Liu Z-B, Kuai D-J, et al. Retinal image graph-cut segmentation algorithm using multiscale Hessian-enhancement-based nonlocal mean filter. Comput Math Methods Med 2013;2013:7927285. http://dx.doi.org/10.1155/2013/927285.
• [22] Laaksonen L, Herttuainen J, Uusitalo H, Lensu L. Refining coarse manual segmentations with stable probability regions. In: Chen X, Garvin MK, Liu J, Trucco E, Xu Y, editors. OMIA 2015, Held in Conjunction with MICCAI 2015, Munich, Germany. Iowa Research Online; 2015. p. 89–96.
• [23] Joshi GD, Sivaswami J, Krishnadas S. Optic disk and cup segmentation from monocular color retinal images for glaucoma assessment. IEEE Trans Med Imaging 2011;30 (June (6)):1192–205.
• [24] Chan T, Vese L. Active contours without edges. IEEE Trans Image Process 2001;10(2):266–77.
• [25] Tao W, Jin H. Color image segmentation based on mean shift and normalized cut. IEEE Trans Syst Man Cybern 2007;37(8).
• [26] Cui Y, Cao K, Zheng G, Zhang F. An adaptive mean shift algorithm based on LSH. Proc Eng 2011;23:265–9.
• [27] Reza A, Eswaran C, Hati S. Automatic tracing of optic disc and exudates from color fundus images using fixed and variable thresholds. J Med Syst 2009;3(1):73–80.
• [28] DIARETDB0, standard diabetic retinopathy image database, http://www2.it.lut.fi/project/imageret/diaretdb0/.
• [29] DIARETDB1, standard diabetic retinopathy image database, http://www2.it.lut.fi/project/imageret/diaretdb1/.

Uwagi

PL

Opracowanie ze środków MNiSW w ramach umowy 812/P-DUN/2016 na działalność upowszechniającą naukę.