Automatic Detection and Classification of Diabetic Retinopathy Using Retinal Fundus Images

Authors: A. Biran, P. Sobhe Bidari, A. Almazroe V. Lakshminarayanan, K. Raahemifar

Abstract:

Diabetic Retinopathy (DR) is a severe retinal disease which is caused by diabetes mellitus. It leads to blindness when it progress to proliferative level. Early indications of DR are the appearance of microaneurysms, hemorrhages and hard exudates. In this paper, an automatic algorithm for detection of DR has been proposed. The algorithm is based on combination of several image processing techniques including Circular Hough Transform (CHT), Contrast Limited Adaptive Histogram Equalization (CLAHE), Gabor filter and thresholding. Also, Support Vector Machine (SVM) Classifier is used to classify retinal images to normal or abnormal cases including non-proliferative or proliferative DR. The proposed method has been tested on images selected from Structured Analysis of the Retinal (STARE) database using MATLAB code. The method is perfectly able to detect DR. The sensitivity specificity and accuracy of this approach are 90%, 87.5%, and 91.4% respectively.

Keywords: Diabetic retinopathy, fundus images, STARE, Gabor filter, SVM.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1125443

References:

[1] C. Aravind, M.PonniBala and S.Vijayachitra, “Autmatic Detection of Microaneurysms and Classifications of Diabetic Retinopathy Images using SVM Technique,” International Journal of Computer Applications, pp. 18-22.
[2] S. SujithKumar and S. Vipula, “Automatic Detection of Diabetic Retinopathy in non-detailed RGB Retinal Fundus Images,” International Journal of Computer Applications, vol. 47, pp. 26-32, June 2012.
[3] K. sangramsing, M. Raju, B. Suvarnsing and K. Charansing, “Non-proliferative Diabetic Retinopathy detection using automatic image processing technique, “ Journal of Pharmacy and Biological Sciences, vol. 10, pp. 33-38, December 2015.
[4] T. Handayani and A. Ayse, “Classification of Non-Proliferative Diabetic Retinopathy Based on Segmented Exudates using K-Means Clustering, “ International Journal Image, Graphics and Signal Processing, pp. 1-8.
[5] N. Kleawsirikul, S. Gulati and B. Uyyanonvara, “Automated Retinal Hemorrhage Detection using Morphological Top Hat and Rule-based Classification,” 3rd International Conference on Intelligent Computational Systems, April 2013.
[6] C. Sundhar and D. Archana, “Automatic Screening of Fundus Images for Detection of Diabetic Retinopathy, “International Journal of Communication and Computer Technologies, vol. 2, April 2014.
[7] H. Li, and O. Chutatape, “Fundus image features extraction,” 22nd Annual EMBS International Conference, “ Chicago, vol. 4, pp. 3071-3073, July 2000.
[8] R A Simandjuntak, A B Suksmono, T L R Mengkoand and I Sovani “Development of computer-aided diagnosis system for early diabetic retinopathy based on microaneurysms detection from retinal images”, 7th International workshop on Enterprise networking and Computing in Health Care Industry, pp.364-367, 2005.
[9] A. Usman , S. Khalid, and S. Khan “Identification and classification of microaneurysms for early detection of diabetic retinopathy”, The Journal of the Pattern Recognition Society, pp.1-11, 2012.
[10] W. Thomas, M. Pascal, E Ali, O. Ricahrd, J.Clotilde and K. Jean-Claude “Automatic detection of microaneurysms in color fundus images” International Journal of Medical Image Analysis, pp.555-566, 2007.