Retinal Vessel Extraction and Fovea Detection Using Morphological Processing

  • Avik Banerjee
  • Soumyadeep Bhattacharjee
  • Sk. Latib
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 710)

Abstract

Extraction of blood vessels from retinal fundus images is a primary phase in the diagnosis of several eye disorders including diabetic retinopathy, a leading cause of vision impairment among working-age adults globally. Since manual detection of blood vessels by ophthalmologists gets progressively difficult with increasing scale, automated vessel detection algorithms provide an efficient and cost-effective alternative to manual methods. This paper aims to provide an efficient and highly accurate algorithm for the extraction of retinal blood vessels. The proposed algorithm uses morphological processing, background elimination, neighborhood comparison for preliminary detection of the vessels. Detection and removal of fovea, and bottom-hat filtering are performed subsequently to improve the accuracy, which is then calculated as a percentage with respect to ground truth images.

Keywords

Diabetic retinopathy Vessel extraction Fovea detection Fundus image Bottom-hat filter Neighborhood comparison 

References

  1. 1.
    Abramoff, Michael, Garvin, Mona, Sonka, Milan: Retinal Imaging and Image Analysis, IEEE Transactions on Medical Imaging, Jan. 2010Google Scholar
  2. 2.
    Chang, Samuel H, Gong Leiguang, Li, Maoqing, Hu, Xiaoying, Yan, Jingwen: Small retinal vessel extraction using modified Canny edge detection, International Conference on Audio, Language and Image Processing, 2008.Google Scholar
  3. 3.
    Chaudhuri, S, Chatterjee, S, Katz, N, Nelson, M, Goldbaum, M: Detection of blood vessels in retinal images using two-dimensional matched filters, IEEE Transactions on Medical Imaging, Volume: 8, Issue: 3, Sept. 1989Google Scholar
  4. 4.
    Fraz, M.M., Barman, S, Remagnino, P, Hoppe, A, Basit, A., Uyyanonvara, B, Rudnicka, A. R., and Owen, C.G.: An Approach To Localize The Retinal Blood Vessels Using Bit Planes And Centerline Detection, Comp. Methods and Progs in Biomed., vol. 108, no. 2, 2012Google Scholar
  5. 5.
    Marin, D., Aquino, A., Gegndez-Arias, M.E., and Bravo, J.M: A New Supervised Method For Blood Vessel Segmentation In Retinal Images By Using Gray-Level And Moment Invariants-Based Features, IEEE Trans. Med. Imaging, vol. 30, no. 1, pp. 146–158, 2011.Google Scholar
  6. 6.
    Miri, M.S. and Mahloojfar, A.: Retinal Image Analysis Using Curvelet Transform and Multistructure Elements Morphology by Reconstruction, IEEE Trans. on Biomed. Eng, vol. 58, pp. 1183–1192, May 2011.Google Scholar
  7. 7.
    Prevention of Blindness from Diabetes Mellitus, Report of a WHO consultation in Geneva, Switzerland, Nov. 2005.Google Scholar
  8. 8.
    Ricci, Elisa, Perfetti, Renzo: Retinal Blood Vessel Segmentation Using Line Operators and Vector Classification, IEEE Trans. on Medical Imaging, Volume: 26, Issue: 10, Oct. 2007Google Scholar
  9. 9.
    Salazar-Gonzalez, A., Kaba, D, Li, Y, and Liu, X: Segmentation Of Blood Vessels And Optic Disc In Retinal Images, IEEE Journal of Biomedical and Health Informatics, 2014.Google Scholar
  10. 10.
    Soares, J. V. B., Leandro, J. J. G., Cesar, R. M., H. Jelinek, F, and Cree, M.J.: Retinal Vessel Segmentation Using The 2-D Gabor Wavelet And Supervised Classification, IEEE Trans. Med. Imaging, vol. 25, no. 9, pp. 1214–1222, 2006.Google Scholar
  11. 11.
    Staal, Joel, Abramoff, Michael, Niemeijer, Meindert, Vuergever, Max, Ginneken, Bram van: Ridge-Based Vessel Segmentation in Color Images of the Retina, IEEE Transactions on Medical Imaging, Vol. 3 Issue 4, Apr. 2004.Google Scholar
  12. 12.
    Zhang, B, Zhang, L, Karray, F: Retinal Vessel Extraction by Matched Filter with First Order Derivative of Gaussian, Comp. in Bio. And Med., vol 40, no 4, 2010.Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  • Avik Banerjee
    • 1
  • Soumyadeep Bhattacharjee
    • 1
  • Sk. Latib
    • 1
  1. 1.Department of Computer Science and EngineeringSt. Thomas’ College of Engineering and TechnologyKolkataIndia

Personalised recommendations