Unsupervised Morphological Approach for Retinal Vessel Segmentation

  • B. V. Santhosh Krishna
  • T. Gnanasekaran
  • S. Aswini
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 710)


Glaucoma, diabetic retinopathy, atherosclerosis, hypertensive retinopathy, age-related macular degeneration (AMD), retinopathy of prematurity (ROP) are some of the retinal diseases which may lead to blindness manifest as artifacts in the retinal images. For the early diagnosis of these systemic diseases, retinal vessel segmentation of retinal is initial assignment. In present scenario, retinal blood vessel segmentation automatically and accurately remains as a challenging task in computer-aided analysis of fundus images. In this paper, we put forward an unsupervised morphological approach for automatically extracting blood vessels from retinal fundus images that can be used in the computer-based analysis. Proposed method uses mathematical morphology with modified top-hat transform for preprocessing and hysteresis thresholding for the segmentation of blood vessels. The proposed approach was evaluated on the DRIVE database and is compared with the recent approaches. Proposed method achieved an average accuracy of 95.95% and best accuracy of 97.01% shows that the approach is efficient.


Morphology Retinal diseases Vessel segmentation Top-hat transform 


  1. 1.
    Fraz, M.M., Remagnino, P., Hopper, A., Uyyanonavara, B., Rudnicka, C., Owen,G.: Blood Vessel Segmentation Methodologies in Retinal images- A survey. Computer Methods and Programs in Biomedicine, Vol. 108 (2012) 407–433Google Scholar
  2. 2.
    Abramoff, M.D., Folk, J.C., Han, D.P., Walker, J.D., Willliams, D.F., Russell, S.R.: Automated Analysis for Detection Referable Diabetic Retinopathy. Jama Opthalmology, Vol 131 (2013) 351–357Google Scholar
  3. 3.
    Yusup, M., Chen, X.Y.: Epidemiology survey of visual loss. International Journal of opthalmology Vol. 10, No. 2 (2012) 304–307Google Scholar
  4. 4.
    Azzopardi, G., Strisciuglio, N., Vento, M., Perkov.: Trainable COSFIRE filters for vessel delination with application to retinal images. Medical Image Analysis, Vol 19 (2015) 46–57Google Scholar
  5. 5.
    Abramoff, M.D., Garvin, M.K., Sonaka, M.: Retinal Imaging and Analysis. IEEE Reviews in Biomedical Engineering, Vol. 3 (2010) 169–208Google Scholar
  6. 6.
    Lupascu, C., Tegolo, D.: Automatic unsupervised segmentation of retinal vessels using self-organizing maps and K-means clustering. Computational Intelligence Methods for Bioinformatics and Biostatistics (2011) 263–274Google Scholar
  7. 7.
    Moazam Fraz, M., Alicja, R., Rudnicka, C., Owen, G., Sarah.: Delineation of Blood Vessels in Pediatric retinal images using decision trees-based ensemble classification, International journal of computer assisted radiology and surgery (2013) 1–17Google Scholar
  8. 8.
    Yin, Y., Adel, M., Bourennane, S.: Automatic Segmentation and Measurement of Vasculature in Retinal Fundus Images Using Probabilistic Formulation Computational and Mathematical Methods in Medicine Vol. 2013 (2013)Google Scholar
  9. 9.
    Nguyen, U.T.V., Bhuiyan, A., Park, L.A.F., Ramamohanrao, K.: An effective retinal blood vessel segmentation method using multi-scale line detection. Pattern Recognition, Vol. 46 (2013) 703–715Google Scholar
  10. 10.
    Roychowdhury, S., Koozekanani, D., Keshab, K., Parhi.: Blood Vessel Segmentation of Fundus images by Major Vessel Extraction and Sub-Image Classification. Biomedical and Health Informatics, IEEE Journal (2014) 2168–2194Google Scholar
  11. 11.
    Sohini Roychowdhury., Koozekani, D., Keshab, K, Parhi.: Iterative Vessel Segmentation of Fundus Images. IEEE Transactions on Biomedical Engineering, Vol. 62 (2015) 1738–1749Google Scholar
  12. 12.
    Bao, X.R., Zhang, S.: Segmentation of retinal blood vessels based on cake filter. Biomed Research International, Vol. 2015 (2015)Google Scholar
  13. 13.
    Mapayi, T., Viriri, S.,Tapamo, J.R.: Adaptive Thresholding Technique for Retinal Vessel se gmentation based on GLCM energy information. Computational and Mathematical Methods in Medicine, Vol. 2015 (2015)Google Scholar
  14. 14.
    Zafer Yavuz., Cemal Kose.: Blood Vessel Extraction in Color Retinal Fundus Images with enhancement filtering and Unsupervised Classification. Hindawi Journal of Healthcare Engineering, Vol. 2017 (2017)Google Scholar
  15. 15.
    Staal, J.J., Abramoff, M.D., Niemeijer, M., Viergever, M, A. Vaan Ginnekan.: Ridge based vessel segmentation in color images of the retina, IEEE Transactions on Medical Imaging, Vol. 23 (2004) 501–509Google Scholar
  16. 16.
    Soares, J.V.B., Leandro, J.J.G., Cesar, R.M.: Ridge based vessel segmentation in color images of the retina, IEEE Transactions on Medical Imaging, Vol. 23 (2006) 1214–1222Google Scholar
  17. 17.
    Lupascu, A., Tegolo, D., Trucco, E.: Retinal vessel segmentation using AdaBoost, IEEE Transactions on Information Technology Biomedicine, Vol.14, No.5 (2010) 1267–1274Google Scholar
  18. 18.
    Cheng, E.K., Du, L., Wu, Y., Zhu, Y.J., Megalooikonomou., Ling, H.B.: Discriminative vessel segmentation in retinal images by fusing context-aware hybrid features, Machine Vision and Applications, Vol. 25, (2014) 1779–1792Google Scholar
  19. 19.
    Mendonca, A., Campilho, A.C.: Segmentation of retinal blood vessels by combining the detection of centerlines and morphological reconstruction. IEEE Transactions of Medical Imaging, (2007) 1200–1213Google Scholar
  20. 20.
    Alexandru Paul Condurache, Til Aach.: Vessel Segmentation in Angiograms using Hysteresis Thresholding. Proceedings of the IAPR Conference on Machine Vision Applications (2005) Tsukuba Science City, JapanGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  • B. V. Santhosh Krishna
    • 1
  • T. Gnanasekaran
    • 2
  • S. Aswini
    • 3
  1. 1.Velammal Institute of TechnologyChennaiIndia
  2. 2.RMK Engineering CollegeChennaiIndia
  3. 3.S A Engineering CollegeChennaiIndia

Personalised recommendations