Automatic classification of retinal blood vessels based on multilevel thresholding and graph propagation


Several systemic diseases affect the retinal blood vessels, and thus, their assessment allows an accurate clinical diagnosis. This assessment entails the estimation of the arteriolar-to-venular ratio (AVR), a predictive biomarker of cerebral atrophy and cardiovascular events in adults. In this context, different automatic and semiautomatic image-based approaches for artery/vein (A/V) classification and AVR estimation have been proposed in the literature, to the point of having become a hot research topic in the last decades. Most of these approaches use a wide variety of image properties, often redundant and/or irrelevant, requiring a training process that limits their generalization ability when applied to other datasets. This paper presents a new automatic method for A/V classification that just uses the local contrast between blood vessels and their surrounding background, computes a graph that represents the vascular structure, and applies a multilevel thresholding to obtain a preliminary classification. Next, a novel graph propagation approach was developed to obtain the final A/V classification and to compute the AVR. Our approach has been tested on two public datasets (INSPIRE and DRIVE), obtaining high classification accuracy rates, especially in the main vessels, and AVR ratios very similar to those provided by human experts. Therefore, our fully automatic method provides the reliable results without any training step, which makes it suitable for use with different retinal image datasets and as part of any clinical routine.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7


  1. 1.

    World Health Organization:


  1. 1.

    Cheung, C.Y., Ikram, M.K., Klein, R., Wong, T.Y.: The clinical implications of recent studies on the structure and function of the retinal microvasculature in diabetes. Diabetologia 58(5), 871 (2015)

    Article  Google Scholar 

  2. 2.

    Muraoka, Y., Tsujikawa, A., Kumagai, K., Akiba, M., Ogino, K., Murakami, T., Akagi-Kurashige, Y., Miyamoto, K., Yoshimura, N.: Age-and hypertension-dependent changes in retinal vessel diameter and wall thickness: an optical coherence tomography study. Am. J. Ophthalmol. 156(4), 706 (2013)

    Article  Google Scholar 

  3. 3.

    Heitmar, R., Lip, G., Ryder, R., Blann, A.: Retinal vessel diameters and reactivity in diabetes mellitus and/or cardiovascular disease. Cardiovasc. Diabetol. 16(1), 56 (2017)

    Article  Google Scholar 

  4. 4.

    Ding, J., Wai, K.L., McGeechan, K., et al.: Retinal vascular caliber and the development of hypertension: a meta-analysis of individual participant data. J. Hypertens. 32(2), 207 (2014)

    Article  Google Scholar 

  5. 5.

    Daien, V., Carriere, I., Kawasaki, R., Cristol, J.P., Villain, M., Fesler, P., Ritchie, K., Delcourt, C.: Retinal vascular caliber is associated with cardiovascular biomarkers of oxidative stress and inflammation: the pola study. PLoS ONE 8(7), e71089 (2013)

    Article  Google Scholar 

  6. 6.

    Seidelmann, S.B., Claggett, B., Bravo, P., Gupta, A., Farhad, H., Di Carli, M., Solomon, S.: Retina vessel caliber in atherosclerotic cardiovascular event prediction: the atherosclerosis in communities study. J. Am. Coll. Cardiol. 67(13), 1893 (2016)

    Article  Google Scholar 

  7. 7.

    Fraz, M.M., Remagnino, P., Hoppe, A., Uyyanonvara, B., Rudnicka, A.R., Owen, C.G., Barman, S.A.: Blood vessel segmentation methodologies in retinal images-a survey. Comput. Methods Programs Biomed. 108(1), 407 (2012)

    Article  Google Scholar 

  8. 8.

    Montoro, A., Morales, S., Naranjo, V., Lopez-Mir, F., Alcaniz, M.: Feature extraction for retinal vascular network classification. In: IEEE-EMBS International Conference on Biomedical and Health Informatics , pp. 404–407 (2014)

  9. 9.

    Irshad, S., Akram, M.U., Ayub, S., Ayaz, A.: Retinal blood vessels differentiation for calculation of arterio-venous ratio. In: International Conference Image Analysis and Recognition , pp. 411–418 (2015)

  10. 10.

    Relan, D., Ballerini, L., Trucco, E., MacGillivray, T.: Machine Intelligence and Signal Processing, pp. 77–84. Springer, Berlin (2016)

    Book  Google Scholar 

  11. 11.

    Xu, X., Ding, W., Abràmoff, M.D., Cao, R.: An improved arteriovenous classification method for the early diagnostics of various diseases in retinal image. Comput. Methods Programs Biomed. 141, 3 (2017)

    Article  Google Scholar 

  12. 12.

    Akbar, S., Akram, M.U., Sharif, M., Tariq, A., Khan, S.A.: Decision support system for detection of hypertensive retinopathy using arteriovenous ratio. Artif. Intell. Med. 90, 15 (2018)

    Article  Google Scholar 

  13. 13.

    Huang, F., Dashtbozorg, B., Tan, T., ter Haar Romeny, B.M.: Retinal artery/vein classification using genetic-search feature selection. Comput. Methods Programs Biomed. 161, 197 (2018)

    Article  Google Scholar 

  14. 14.

    Mirsharif, Q., Tajeripour, F., Pourreza, H.: Automated characterization of blood vessels as arteries and veins in retinal images. Comput. Med. Imaging Graph. 37(7), 607 (2013)

    Article  Google Scholar 

  15. 15.

    Joshi, V.S., Reinhardt, J.M., Garvin, M.K., Abramoff, M.D.: Automated method for identification and artery-venous classification of vessel trees in retinal vessel networks. PLoS ONE 9(2), e88061 (2014)

    Article  Google Scholar 

  16. 16.

    Dashtbozorg, B., Mendonça, A.M., Campilho, A.: An automatic graph-based approach for artery/vein classification in retinal images. IEEE Trans. Image Process. 23(3), 1073 (2014)

    MathSciNet  MATH  Article  Google Scholar 

  17. 17.

    Estrada, R., Allingham, M.J., Mettu, P.S., Cousins, S.W., Tomasi, C., Farsiu, S.: Retinal artery-vein classification via topology estimation. IEEE Trans. Med. Imaging 34(12), 2518 (2015)

    Article  Google Scholar 

  18. 18.

    Hu, Q., Abràmoff, M.D., Garvin, M.K.: Automated construction of arterial and venous trees in retinal images. J. Med. Imaging 2(4), 044001 (2015)

    Article  Google Scholar 

  19. 19.

    Pellegrini, E., Robertson, G., MacGillivray, T., van Hemert, J., Houston, G., Trucco, E.: A graph cut approach to artery/vein classification in ultra-widefield scanning laser ophthalmoscopy. IEEE Trans. Med. Imaging 37(2), 516 (2017)

    Article  Google Scholar 

  20. 20.

    Zhao, Y., Xie, J., Zhang, H., Zheng, Y., Zhao, Y., Qi, H., Zhao, Y., Su, P., Liu, J., Liu, Y.: Retinal vascular network topology reconstruction and artery/vein classification via dominant set clustering. IEEE Trans. Med. Imaging 39(2), 341–356 (2020)

    Article  Google Scholar 

  21. 21.

    Meyer, M.I., Galdran, A., Costa, P., Mendonça, A.M., Campilho, A.: Deep convolutional artery/vein classification of retinal vessels. In: International Conference Image Analysis and Recognition , pp. 622–630 (2018)

  22. 22.

    Galdran, A., Meyer, M.I., Costa, P., Mendonça, A.M., Campilho, A.: Uncertainty-aware artery/vein classification on retinal images. In: IEEE International Symposium on Biomedical Imaging , pp. 556–560 (2019)

  23. 23.

    Niemeijer, M., Xu, X., Dumitrescu, A.V., Gupta, P., van Ginneken, B., Folk, J.C., Abràmoff, M.D.: Automated measurement of the arteriolar-to-venular width ratio in digital color fundus photographs. IEEE Trans. Med. Imaging 30(11), 1941 (2011)

    Article  Google Scholar 

  24. 24.

    Vázquez, S., Barreira, N., Penedo, M.G., Rodríguez-Blanco, M.: Reliable monitoring system for arteriovenous ratio computation. Comput. Med. Imaging Graph. 37(5), 337 (2013)

    Article  Google Scholar 

  25. 25.

    Dashtbozorg, B., Mendonça, A.M., Campilho, A.: Assessment of retinal vascular changes through arteriolar-to-venular ratio calculation. In: International Conference Image Analysis and Recognition , pp. 335–343 (2015)

  26. 26.

    Mustafa, W.A., Yazid, H., Yaacob, S.B.: Illumination correction of retinal images using superimpose low pass and Gaussian filtering. In: International Conference on Biomedical Engineering , pp. 1–4 (2015)

  27. 27.

    Varnousfaderani, E.S., Yousefi, S., Belghith, A., Goldbaum, M.H.: Luminosity and contrast normalization in color retinal images based on standard reference image. In: Styner, M.A., Angelini, E.D. (eds.) Medical Imaging 2016: Image Processing, vol. 9784, pp. 966–971. SPIE, Bellingham (2016)

    Google Scholar 

  28. 28.

    Huang, F., Dashtbozorg, B., ter Haar Romeny, B.M.: Artery/vein classification using reflection features in retina fundus images. Mach. Vis. Appl. 29(1), 23 (2018)

    Article  Google Scholar 

  29. 29.

    Dashtbozorg, B.: Advanced image analysis for the assessment of retinal vascular changes, Ph.D Thesis, Universidade do Porto. (2015)

  30. 30.

    Niemeijer, M., Xu, X., Dumitrescu, A., Gupta, P., van Ginneken, B., Folk, J., Abràmoff, M.: INSPIRE-AVR: iowa normative set for processing images of the retina—artery vein ratio. (2011)

  31. 31.

    Dashtbozorg, B., Mendonça, A.M., Campilho, A.: Optic disc segmentation using the sliding band filter. Comput. Biol. Med. 56, 1 (2015)

    Article  Google Scholar 

  32. 32.

    Mendonca, A.M., Campilho, A.: Segmentation of retinal blood vessels by combining the detection of centerlines and morphological reconstruction. IEEE Trans. Med. Imaging 25(9), 1200 (2006)

    Article  Google Scholar 

  33. 33.

    Mendonça, A.M., Remeseiro, B., Dashtbozorg, B., Campilho, A.: Automatic and semi-automatic approaches for arteriolar-to-venular computation in retinal photographs. In: Armato, S.G., Petrick, N.A. (eds.) Medical Imaging 2017: Computer-Aided Diagnosis, vol. 10134, pp. 402–408. SPIE, Bellingham (2017)

    Google Scholar 

  34. 34.

    Foracchia, M., Grisan, E., Ruggeri, A.: Luminosity and contrast normalization in retinal images. Med. Image Anal. 9(3), 179 (2005)

    Article  Google Scholar 

  35. 35.

    Schneiderman, H.: The Funduscopic Examination. Butterworths, London (1990)

    Google Scholar 

  36. 36.

    Otsu, N.: A threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybern. 9(1), 62 (1979)

    Article  Google Scholar 

  37. 37.

    Knudtson, M.D., Lee, K.E., Hubbard, L.D., Wong, T.Y., Klein, R., Klein, B.E.: Revised formulas for summarizing retinal vessel diameters. Curr. Eye Res. 27(3), 143 (2003)

    Article  Google Scholar 

  38. 38.

    Lyu, X., Yang, Q., Xia, S., Zhang, S.: Construction of retinal vascular trees via curvature orientation prior. In: IEEE International Conference on Bioinformatics and Biomedicine , pp. 375–382 (2016)

  39. 39.

    Demšar, J.: Statistical comparisons of classifiers over multiple data sets. J. Mach. Learn. Res. 7, 1 (2006)

    MathSciNet  MATH  Google Scholar 

  40. 40.

    Niemeijer, M., Staal, J.J., Ginneken, B.V., Loog, M., Abràmoff, M.D.: DRIVE: digital retinal images for vessel extraction. (2004)

  41. 41.

    Hu, Q., Garvin, M.K., Abràmoff, M.D.: RITE: Retinal images vessel tree extraction. (2015)

Download references


Beatriz Remeseiro acknowledges the support of the Portuguese funding agency, FCT – Fundação para a Ciência e a Tecnologia, under Post-doctoral Fellowship program (ref. SFRH/BPD/111177/2015).

Author information



Corresponding author

Correspondence to Beatriz Remeseiro.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Remeseiro, B., Mendonça, A.M. & Campilho, A. Automatic classification of retinal blood vessels based on multilevel thresholding and graph propagation. Vis Comput (2020).

Download citation


  • Retinal images
  • Artery/vein classification
  • Arteriolar-to-venular ratio
  • Multilevel thresholding
  • Graph propagation