Retinal Vessel Classification Based on Maximization of Squared-Loss Mutual Information

  • D. Relan
  • L. Ballerini
  • E. Trucco
  • T. MacGillivray
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 390)


The classification of retinal vessels into arterioles and venules is important for any automated system for the detection of vascular changes in the retina and for the discovery of biomarkers associated with systemic diseases such as diabetes, hypertension, and cardiovascular disease. We introduce Squared-loss Mutual Information clustering (SMIC) for classifying arterioles and venules in retinal images for the first time (to the best of our knowledge). We classified vessels from 70 fundus camera images using only 4 colour features in zone B (802 vessels) and in an extended zone (1,207 vessels). We achieved an accuracy of 90.67 and 87.66 % in zone B and the extended zone, respectively. We further validated our algorithm by classifying vessels in zone B from two publically available datasets—INSPIRE-AVR (483 vessels from 40 images) and DRIVE (171 vessels from 20 test images). The classification rates obtained on INSPIRE-AVR and DRIVE dataset were 87.6 and 86.2 %, respectively. We also present a technique to sort the unclassified vessels which remained unlabeled by the SMIC algorithm.


Retinal Fundus Vessels Arterioles Venules Classification  Clustering 



This work is supported by Leverhulme Trust grant RPG-419 “Discovery of retinal biomarkers for genetics with large cross-linked datasets”, and part of the VAMPIRE (Vasculature Assessment and Measurement Platform for Images of the REtina) project led by the University of Dundee and Edinburgh, UK [5]. We thank Dr. Jim Wilson, University of Edinburgh, for making the ORCADES images available.


  1. 1.
    Abràmoff, M.D., et al.: Retinal imaging and image analysis. IEEE Rev. Biomed. Eng. 3, 169–208 (2010)CrossRefGoogle Scholar
  2. 2.
    Wong, T.Y., et al.: Computer-assisted measurement of retinal vessel diameters in the Beaver Dam Eye Study: methodology, correlation between eyes, and effect of refractive errors. American academy of ophthalmology, pp. 90–1183 (2004)Google Scholar
  3. 3.
    Ikram, M.K., et al.: Retinal vessel diameters and risk of hypertension: the rotterdam study, hypertension. J. Am. Hear. Assoc. 47(2), 94–189 (2006)Google Scholar
  4. 4.
    Leung, H., et al.: Relationships between age, blood pressure, and retinal vessel diameters in an older population. Investig. Ophthalmol Vis. Sci. 44(7), 2900–2904 (2003)CrossRefGoogle Scholar
  5. 5.
    Perez-Rovira, A., et al.: Vampire: vessel assessment and measurement platform for images of the retina. In: Proceedings of the IEEE Engineering in Medicine and Biology Society, pp. 3391–3394 (2011)Google Scholar
  6. 6.
    Li, H., Hsu, W., Lee, M., Wong, T.Y.: Automatic grading of retinal vessel calibre. IEEE Trans. Bio-med. Eng. 52(7), 5–1352 (2005)CrossRefGoogle Scholar
  7. 7.
    Cheung, C.Y.-L., Hsu, W., et al.: A new method to measure peripheral retinal vascular calibre over an extended area. Microcirculation 17(7), 495–503 (2010)Google Scholar
  8. 8.
    Sugiyama, M., et al.: Information-Maximization Clustering based on Squared-Loss Mutual Information, pp. 40–20111Google Scholar
  9. 9.
    Jelinek, H.F., et al.: Towards vessel characterization in the vicinity of the optic disc in digital retinal images. In: Proceedings of the Image and vision computing (2005)Google Scholar
  10. 10.
    Niemeijer, M., Xu, X.: Automated measurement of the arteriolar-to-venular width ratio in digital color fundus photographs. IEEE Trans. Med. Imaging 30(11), 50–1941 (2011)CrossRefGoogle Scholar
  11. 11.
    Mirsharif, Q.: Automated characterization of blood vessels as arteries and veins in retinal images. Comput. Med. Imaging Graph. 37(7–8), 17–607 (2013)Google Scholar
  12. 12.
    Dashtbozorg, B., et al.: An automatic graph-based approach for artery/vein classification in retinal images. IEEE Trans. Image Process. 23(3), 1073–1083 (2014)MathSciNetCrossRefGoogle Scholar
  13. 13.
    Relan, D., et al.: Retinal vessel classification: sorting arteries and veins. In: Conference Proceedings: Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 7396–7399 (2013)Google Scholar
  14. 14.
    Relan, D., et al.: Automatic retinal vessel classification using a least square-support vector machine in VAMPIRE’. In: 35th Annual International Conference of the IEEE EMBS Engineering in Medicine and Biology Society (EMBC), pp. 142–145. Chicago, USA (2014)Google Scholar
  15. 15.
    Saez, M., et al.: Development of an automated system to classify retinal vessels into arteries and veins. Comput. Methods programs Biomed. 1–10 (2012)Google Scholar
  16. 16.
    Vazquez, S.G., et al.: On the automatic computation of the Arterio-Venous Ratio in retinal images: using minimal paths for the Artery/Vein classification. In: International Conference on Digital Image Computing: Techniques and Applications, pp. 599–604 (2010)Google Scholar
  17. 17.
    Grisan, E., Ruggeri., A.: A divide et impera strategy for automatic classification of retinal vessels into arteries and veins, In: Proceedings of the 25th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 890–893 (2003)Google Scholar
  18. 18.
    Joshi, V.S., et al.: Automated artery-venous classification of retinal blood vessels based on structural mapping method. In: Proceedings of the SPIE, vol. 8315 (2012)Google Scholar
  19. 19.
    Staal, J.J., Abramoff, M.D.: Ridge based vessel segmentation in color images of the retina. IEEE Trans. Med. Imaging 23, 501–509 (2004)CrossRefGoogle Scholar
  20. 20.
    Chrástek, R., et al.: Automated segmentation of the optic nerve head for diagnosis of glaucoma. Med. Image Anal. 9(4), 297–314 (2005)CrossRefGoogle Scholar

Copyright information

© Springer India 2016

Authors and Affiliations

  • D. Relan
    • 1
  • L. Ballerini
    • 2
  • E. Trucco
    • 2
  • T. MacGillivray
    • 1
    • 3
    • 4
  1. 1.Centre for Clinical Brain SciencesEdinburghUK
  2. 2.School of ComputingUniversity of DundeeDundeeUK
  3. 3.Clinical Research Imaging CentreUniversity of EdinburghEdinburghUK
  4. 4.Clinical Research FacilityUniversity of EdinburghEdinburghUK

Personalised recommendations