Exudates Identification and Classification using Kirsch Template and K-means Clustering in Fundus Eye Images

Authors

  • Megala Sivakumar  Ph.D Scholar Dept.of Computer and Information Science Annamalai University, Annamalai Nagar, India.
  • Dr. T. S. Subashini  Associate Professor Department of Computer Science & Engineering Annamalai University, Annamalai Nagar, India
  • G. Sivaranjani  ME Student Department of Computer Science & Engineering Annamalai University, Annamalai Nagar, India

Keywords:

Optic disk, fundus image, segmentation, Kirsch template, thresholding, morphological operations, k-means clustering, connected component labeling, SVM classifier.

Abstract

Diabetic retinopathy (DR) which is caused due to the damage of blood vessel present in the retina is one of the major diseases that cause vision loss in diabetic patients. Exudates are the preliminary symptoms of diabetic retinopathy; if it is not treated properly it leads to complete blindness. Exudates are nothing but a lipid effusion from blood vessels that are visible signs of retinal abnormality which occurs at an earlier state. However, manual testing and evaluation of the exudates takes much time, effort and also sometimes mistakes in identifying the disease may arise. So in this paper, we have developed a computational tool that can help to detect and classify exudates in fundus images. Initially, Kirsch template followed by morphological operations was applied on the image to detect and eliminate the optic disc. Then the proposed exudates segmentation and classification methodology works by combining different techniques like K-means clustering, connected component labeling and SVM. To test the performance of the system DIARETDB1 fundus image database is used and the results are promising with an overall classification accuracy of 84.68%

References

  1. Christye Sisson, Ophthalmic Imaging: Posterior Segment Imaging, Anterior Eye Photography, and Slit Lamp Biomicrography, Taylor & Francis, 2017
  2. http://www.it.lut.fi/project/imageret/diaretdb0/
  3. V. Esmann , K. Lundbaek, P. H. Madsen, "Types of Exudates in Diabetic Retinopathy", Journal of Internal Medicine, Vol 174, Issue 3, 1963.
  4. M. Lalonde, M. Beaulieu and L. Gagnon, "Fast and robust optic disc detection using pyramidal decomposition and Hausdroff-based template matching",IEEE transactions on medical imaging, Vol 20, No. n, pp. 1193-1200, November, 200l.
  5. DashtbozorgBehdad, Ana Maria Mendonc¸ a, AurelioCampilho, Optic disc segmentation using the sliding band filter, Comput. Biol. Med. 56 (2015) 1–12.
  6. S. Morales, V. Naranjo, J. Angulo, M. Alcaniz, Automatic detection of optic disc based on PCA and mathematical morphology, IEEE Trans. Med. Imaging 32 (2013) 786–796. 46 P.S. Mittapalli, G.B. Kande / Biomedical Signal Processing and Control 24 (2016) 34–46
  7. Aquino Arturo, Manuel Emilio Gegundez, Diego Marin, Detecting the optic disc boundary in digital fundus images using morphological, edge detection, and feature extraction techniques, IEEE Trans. Med. Imaging 29 (11) (2010) 1860–1869.
  8. J. Xu, O. Chutatape, E. Sung, C. Zheng, P.C.T. Kuan, Optic disk feature extraction via modified deformable model technique for glaucoma analysis, Pattern Recognit. 40 (2007) 2063–2076.
  9. F. Mendels, C. Heneghan, J.P. Thiran, Identification of the optic disk boundary in retinal images using active contours, in: Proceedings of the Irish Machine Vision and Image Processing Conference, IMVIP 1999, 1999, pp. 103–115.
  10. D.T. Morris, C. Donnison, Identifying the neuroretinal rim boundary using dynamic contours, J. Image Vis. Comput. 17 (1999) 169–174.
  11. KandeGiriBabu, P.V. Subbaiah, T. SatyaSavithri, Feature extraction in fundus images, J. Med. Biol. Eng. 29 (3) (2009) 122–130.
  12. Feroui Amel et al, "Improvement of the hard exudates detection method used for computer – aided diagnosis of diabetic retinopathy", I.J.Image, Graphics and Signal Processing, DOI: 10.5815/ijigsp.2012.04.03.
  13. H. Li and O. Chutatape, "Automated feature extraction in color retinal images by a model based approach," IEEE Trans. on Medical Engineering, vol. 51, pp. 246-254, 2004.
  14. C. I. Sanchez, M. Garcia, A. Mayo, M. Lopez and R. Hornero, "Retinal image analysis based on mixture models to detect hard exudates," Medical Image Analysis, vol. 13, pp. 650-658, 2009.
  15. M. Garcia, C. I. Sanchez, M. I. Lopez, D. Abasolo and R. Hornero, "Neural network based detection of hard exudates in retinal images," Computer Methods and Programs in Biomedicine, vol. 93, pp.9-19, 2009.
  16. AkaraSopharak, BunyaritUyyanonvara, Sarah Barman proposed an "Automatic exudates detection fordiabetic retinopathy screening" doi:10.2306/scienceasia1513-1874.2009.35.080
  17. Gudmundsson, M., E.A. El-Kwae and M.R. Kabuka,m 1998. Edge detection in medical images using a genetic algorithm, IEEE Transactions on IEEE Transactions on Medical Imaging, 17(3): 469-474.
  18. R. S. Biyani, B. M. Patre, "A clustering approach for exudates detection in screening of diabetic retinopathy", IEEE International Conference on Signal and Information Processing (IConSIP), 2016 DOI: 10.1109/ICONSIP.2016.7857495
  19. Soju George and Bhailal Limbasiya, "A Review Paper On Detection And Extraction Of Blood Vessels, Microaneurysms And Exudates From Fundus Images", International Journal of Scientific & Technology Research Volume 2, Issue 11, November 2013
  20. Thorsten Joachims. 2002. Learning to Classify Text Using Support Vector Machines: Methods, Theory and Algorithms. Kluwer Academic Publishers, Norwell, MA, USA.

IInternational Journal of Scientific Research in Computer Science, Engineering and Information Technology

Downloads

Published

2018-04-30

Issue

Volume 3, Issue 3, March-April-2018

Section

Research Articles

License

Copyright (c) IJSRCSEIT

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

[1]
Megala Sivakumar, Dr. T. S. Subashini, G. Sivaranjani, " Exudates Identification and Classification using Kirsch Template and K-means Clustering in Fundus Eye Images, IInternational Journal of Scientific Research in Computer Science, Engineering and Information Technology(IJSRCSEIT), ISSN : 2456-3307, Volume 3, Issue 3, pp.1796-1803, March-April-2018.