A Proposed Segmentation and Classification Algorithm of Diabetic Retinopathy Images for Exudates Disease

  • Authors

    • Dr. N. Jayalakshmi
    • K. Priya
    https://doi.org/10.14419/ijet.v7i3.20.22981
  • Diabetic retinopathy, Image segmentation, Image enhancement, Principle Component Analysis, Curvelet Transform
  • The retinal image diagnosis is a significant methodology for diabetic retinopathy analysis. The diabetic retinopathy is a one of the major problematic diseases that provides changes in the blood vessels of the retinal that may issue blindness if it is not properly prevented and should be treated at the early stage. The Principle Component Analysis (PCA) algorithm is proposed to improve the contrast and brightness of the image. This paper presents the novel algorithm for blood vessel segmentation using unsupervised algorithm.  The normalized graph cut segmentation with Curvelet transform is applied to segment the blood vessel to determine the thickness of the blood vessel and it is considered as one of the key feature to classify the diabetic retinopathy. The multi-resolution curvelet transform is used to improve the blood vessel segmentation. The PCA algorithm is used to provide the gradient of the image for accurate segmentation of blood vessel. Optic disc is an important key feature of retinal image that is first process for analysis behavior of disease identification. The optic disc is removed by applying morphological erosion and dilation operation. The proposed localization method consists of Hough transform to detect the circular and elliptic shape of optic disc and extracts the Region of Interest (ROI) containing optic disc. The modified expectation maximization (MEM) algorithm is proposed to segment the hard exudates from the fundus image to identify the disease of diabetics. The Gray level Co-Occurrence Matrix (GLCM) and bandlet transform is applied to calculate the features for classification. The convolution neural network (CNN) is applied to classify the images into normal or abnormal.

     

     

     

  • References

    1. [1] Klein R, Klein BEK, and Moss SE 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. Arch Ophthalmol. 1984, 102:520-526.

      [2] Early Treatment of Diabetic Retinopathy Study Research Group(1991). Early Photocoagulation for diabetic retinopathy:ETDRS report no. 9 Ophthalmology, 1991, 98766–785.

      [3] D. E. Singer, D. M. Nathan, H. A. Fogel, and A. P. Schachat, “Screening for Diabetic Retinopathy,†Annals of Internal Medicine, vol. 116, no. 8, 1992, pp. 60–71.

      [4] M. J. Cree, J. A. Olson, K. C. McHardy, P. F. Sharp, and J. V. Forrester, “The Preprocessing of Retinal Images for the Detection of Fluoresce in Leakage,†Physics in Medicine & Biology, vol. 44, no. 1, 1999, pp. 293–308.

      [5] A. Pinz, M. Prantl, and P. Datlinger, “Mapping the Human Retina,†IEEE Transactions on Medical Imaging, vol. 17, no. 4, 1998, pp. 606–619.

      [6] M. Usman Akram, Anam Tariq, and Shoab A. Khan. Retinal image blood vessel segmentation. Proceedings of the international conference on information and communication technology, 978(1), 2009.

      [7] J. Staal, M. D. Abramoff, M. Niemeijer, M. A. Viergever, and B. van Ginneken. Ridge-based vessel segmentation in color images of the retina. IEEE Transactions on Medical Imaging, 23(4):501–509, 2004.

      [8] [8] J. V. B. Soares. Retinal vessel segmentation using the 2-d gabor wavelet and supervised classification. IEEE Transactions on Medical Imaging, 25(9):1214–1222, 2006.

      [9] Sopharak A, Onvara UB, Barman S, Williamson TH. Auto­matic detection of diabetic retinopathy exudates from non-dilated retinal images using mathematical morphology methods. Computerized Medical Imaging and Graphics. 2008; 32(8):720–7.

      [10] [10]. Shanthi B, Revathy C, Devi AJM, Subhashree. Effect of iron deficiency on glycation of haemoglobin in nondiabetics. Journal of Clinical and Diagnostic Research. 2013; 7(1):15– 7. ISSN: 0973-709X.

      [11] Lochan K, Sah P, Sarma KK. Innovative feature set for reti­nopathic analysis of diabetes and its detection. 3rd National Conference on Emerging Trends and Applications in Com­puter Science (NCETACS); Shilong: Meghalaya. 2012 Mar 30-31. p. 240–5.

      [12] A. Hoover and M. Goldbaum, “Locating the optic nerve in a retinal image using the fuzzy convergence of the blood vessels.,†IEEE Trans. Med. Imaging, vol. 22, no. 8, pp. 951–958, 2003.

      [13] A. Osareh, M. Mirmehdi, B. Thomas, and R. Markham, “Classification and localisation of diabetic-related eye disease,†Comput. Vision—ECCV …, pp. 502–516, 2002.

      [14] A. Osareh, “Automated Identification of Diabetic Retinal Exudates and the Optic Disc,†Department of Computer Sciene, University of Bristol, 2004.

      [15] C. Sinthanayothin, J. F. Boyce, H. L. Cook, and T. H. Williamson, “Automated localisation of the optic disc, fovea, and retinal blood vessels from digital colour fundus images.,†Br. J. Ophthalmol., vol. 83, no. 8, pp. 902–910, 1999.

      [16] Narasimha-Iyer, H., Can, A., Roysam, B., Stewart, C.V., Tanenbaum, H.L., Majerovics, A., Singh, H.: Robust Detection and Classification of Longitudinal Changes in Color Retinal Fundus Images for Monitoring Diabetic Retinopathy. IEEE transactions on biomedical engineering 53(6), 1084–1098 (2006)

      [17] Sinthanayothin, C., Boyce, J.A., Cook, H.L., Williamson, T.H.: Automated localization of the optic disc, fovea, and retinal blood vessels from digital colour fundus images. British Journal of Ophthalmology 83, 902–910 (1999)

      [18] Hoover, A., Goldbaum, M.: Locating the optic nerve in a retinal image using the fuzzy convergence of the blood vessels. IEEE Trans. on Medical Imaging 22(8), 951–958 (2003).

      [19] Mendels, F., Heneghan, C., Thiran, J.P.: Identification of the optic disc boundary in retinal images using active contours. In: Proc. IMVIP conference, pp. 103–115 (1999).

      [20] P. N. Sharath Kumar, R. R. Kumar, A. Sathar and V. Sahasranamam, "Automatic detection of exudates in retinal images using histogram analysis," 2013 IEEE Recent Advances in Intelligent Computational Systems (RAICS), Trivandrum, 2013, pp. 277-281.

      [21] [Carmen Alina Lupascu, Domenico Tegolo Automated Detection of Optic Disc Location in Retinal Images, IEEE Symposium on Computer-Based Medical Systems, IEEE 2008.

  • Downloads

  • How to Cite

    N. Jayalakshmi, D., & Priya, K. (2018). A Proposed Segmentation and Classification Algorithm of Diabetic Retinopathy Images for Exudates Disease. International Journal of Engineering & Technology, 7(3.20), 724-731. https://doi.org/10.14419/ijet.v7i3.20.22981