Journal of Mathematical Imaging and Vision

, Volume 49, Issue 3, pp 583–610 | Cite as

A Multi-Orientation Analysis Approach to Retinal Vessel Tracking

  • Erik BekkersEmail author
  • Remco Duits
  • Tos Berendschot
  • Bart ter Haar Romeny


This paper presents a method for retinal vasculature extraction based on biologically inspired multi-orientation analysis. We apply multi-orientation analysis via so-called invertible orientation scores, modeling the cortical columns in the visual system of higher mammals. This allows us to generically deal with many hitherto complex problems inherent to vessel tracking, such as crossings, bifurcations, parallel vessels, vessels of varying widths and vessels with high curvature. Our approach applies tracking in invertible orientation scores via a novel geometrical principle for curve optimization in the Euclidean motion group SE(2). The method runs fully automatically and provides a detailed model of the retinal vasculature, which is crucial as a sound basis for further quantitative analysis of the retina, especially in screening applications.


Gabor wavelets Oriented wavelets Orientation scores Vessel tracking Retina Retinal vasculature 



The research leading to the results of this article has received funding from the European Research Council under the European Community’s 7th Framework Programme (FP7/2007–2014)/ERC grant agreement No. 335555. This work is also part of the Open image in new window Hé Programme of Innovation Cooperation, which is (partly) financed by the Netherlands Organisation for Scientific Research (NWO).


  1. 1.
    Abramoff, M.D., Garvin, M.K., Sonka, M.: Retinal imaging and image analysis. IEEE Rev. Biomed. Eng. 3, 169–208 (2010) CrossRefGoogle Scholar
  2. 2.
    Al-Diri, B., Hunter, A., Steel, D.: An active contour model for segmenting and measuring retinal vessels. IEEE Trans. Med. Imaging 28(9), 1488–1497 (2009) CrossRefGoogle Scholar
  3. 3.
    Al-Diri, B., Hunter, A., Steel, D., Habib, M.: Automated analysis of retinal vascular network connectivity. Comput. Med. Imaging Graph. 34(6), 462–470 (2010). doi: 10.1016/j.compmedimag.2009.12.013. CrossRefGoogle Scholar
  4. 4.
    Aubin, T.: A Course in Differential Geometry. Graduate Studies in Mathematics, vol. 27 (2001) zbMATHGoogle Scholar
  5. 5.
    August, J.: The curve indicator random field. Ph.D. thesis, Yale University (2001) Google Scholar
  6. 6.
    August, J., Zucker, S.: The curve indicator random field and Markov processes. IEEE Trans. Pattern Anal. Mach. Intell. 25(4), 387–400 (2003) CrossRefGoogle Scholar
  7. 7.
    Bankhead, P., Scholfield, C.N., McGeown, J.G., Curtis, T.M.: Fast retinal vessel detection and measurement using wavelets and edge location refinement. PLoS ONE 7(3), e32435 (2012) CrossRefGoogle Scholar
  8. 8.
    Bekkers, E.: A new retinal vessel tracking method based on orientation scores. Master’s thesis, Department of Biomedical Engineering, Eindhoven University of Technology, the Netherlands (2012) Google Scholar
  9. 9.
    Bergholm, F.: Edge focusing. IEEE Trans. Pattern Anal. Mach. Intell. PAMI-9(6), 726–741 (1987) CrossRefGoogle Scholar
  10. 10.
    Boscain, U., Charlot, G., Rossi, F.: Existence of planar curves minimizing length and curvature. Differential equations and dynamical systems, collected papers. Tr. Mat. Inst. Steklova 270, 49–61 (2010) MathSciNetGoogle Scholar
  11. 11.
    Boscain, U., Duits, R., Rossi, F., Sachkov, Y.: Curve cuspless reconstruction via sub-Riemannian geometry. ESAIM Control Optim. Calc. Var. (2014, to appear). arXiv:1203.3089v4. doi: 10.1051/cocv/2013082
  12. 12.
    Brinchmann-Hansen, O., Heier, H.: Theoretical relations between light streak characteristics and optical properties of retinal vessels. Acta Ophthalmol. 64(S179), 33–37 (1986). doi: 10.1111/j.1755-3768.1986.tb00701.x CrossRefGoogle Scholar
  13. 13.
    Budai, A.: Gold Standard Database for Evaluation of Fundus Image Segmentation Algorithms (2011). Google Scholar
  14. 14.
    Budai, A., Hornegger, J., Michelson, G.: Multiscale approach for blood vessel segmentation on retinal fundus images. Investig. Ophthalmol. Vis. Sci. 50, 325 (2009) Google Scholar
  15. 15.
    Can, A., Shen, H., Turner, J.N., Tanenbaum, H.L., Roysam, B.: Rapid automated tracing and feature extraction from retinal fundus images using direct exploratory algorithms. IEEE Trans. Inf. Technol. Biomed. 3, 125–138 (1999) CrossRefGoogle Scholar
  16. 16.
    Chen, J., Sato, Y., Tamura, S.: Orientation space filtering for multiple orientation line segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 22(5), 417–429 (2000). doi: 10.1109/34.857000 CrossRefGoogle Scholar
  17. 17.
    Chutatape, O., Zheng, L., Krishnan, S.: Retinal blood vessel detection and tracking by matched Gaussian and Kalman filters. In: Proceedings of the 20th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 1998, vol. 6, pp. 3144–3149 (1998) Google Scholar
  18. 18.
    Citti, G., Sarti, A.: A cortical based model of perceptual completion in the roto-translation space. J. Math. Imaging Vis. 24(3), 307–326 (2006) CrossRefMathSciNetGoogle Scholar
  19. 19.
    Duits, R.: Perceptual organization in image analysis. Ph.D. thesis, Department of Biomedical Engineering, Eindhoven University of Technology, the Netherlands (2005) Google Scholar
  20. 20.
    Duits, R., Franken, E.: Left-invariant stochastic evolution equations on SE(2) and its applications to contour enhancement and contour completion via invertible orientation scores. CASA-report and arXiv (2007). arXiv:0711.0951v4.
  21. 21.
    Duits, R., Franken, E.M.: Line enhancement and completion via linear left-invariant scale spaces on SE(2). In: Tai, X.-C. (ed.) Scale Space and Variational Methods in Computer Vision, pp. 795–807 (2009) CrossRefGoogle Scholar
  22. 22.
    Duits, R., Franken, E.: Left-invariant parabolic evolutions on SE(2) and contour enhancement via invertible orientation scores. Part II: non-linear left-invariant diffusions on invertible orientation score. Q. Appl. Math. 68, 293–331 (2010) zbMATHMathSciNetGoogle Scholar
  23. 23.
    Duits, R., Franken, E.: Left-invariant parabolic evolutions on SE(2) and contour enhancement via invertible orientation scores. Part I: linear left-invariant diffusion equations on SE(2). Q. Appl. Math. 68(2), 255–292 (2010) zbMATHMathSciNetGoogle Scholar
  24. 24.
    Duits, R., van Almsick, M.: The explicit solutions of linear left-invariant second order stochastic evolution equations on the 2D-Euclidean motion group. Q. Appl. Math. 66, 27–67 (2008) zbMATHGoogle Scholar
  25. 25.
    Duits, R., Duits, M., van Almsick, M., ter Haar Romeny, B.: Invertible orientation scores as an application of generalized wavelet theory. Pattern Recognit. Image Anal. 17, 438 (2007). doi: 10.1134/S105466180703011X CrossRefGoogle Scholar
  26. 26.
    Duits, R., Felsberg, M., Granlund, G.H., ter Haar Romeny, B.M.: Image analysis and reconstruction using a wavelet transform constructed from a reducible representation of the Euclidean motion group. Int. J. Comput. Vis. 72(1), 79–102 (2007) CrossRefGoogle Scholar
  27. 27.
    Duits, R., Boscain, U., Rossi, F., Sachkov, Y.: Association fields via cuspless sub-Riemannian geodesics in SE(2). J. Math. Imaging Vis. (2012, submitted).
  28. 28.
    Espona, L., Carreira, M.J., Ortega, M., Penedo, M.G.: A snake for retinal vessel segmentation. In: Proceedings of the 3rd Iberian Conference on Pattern Recognition and Image Analysis, Part II. IbPRIA’07, pp. 178–185. Springer, Berlin (2007) CrossRefGoogle Scholar
  29. 29.
    Felsberg, M., Forssen, P.E., Scharr, H.: Channel smoothing: efficient robust smoothing of low-level signal features. IEEE Trans. Pattern Anal. Mach. Intell. 28(2), 209–222 (2006) CrossRefGoogle Scholar
  30. 30.
    Fischer, S., Šroubek, F., Perrinet, L., Redondo, R., Cristóbal, G.: Self-invertible 2D log-Gabor wavelets. Int. J. Comput. Vis. 75(2), 231–246 (2007). doi: 10.1007/s11263-006-0026-8 CrossRefGoogle Scholar
  31. 31.
    Florack, L., Kuijper, A.: The topological structure of scale-space images. J. Math. Imaging Vis. 79, 65–79 (2000). CrossRefMathSciNetGoogle Scholar
  32. 32.
    Frangi, A.F., Niessen, W.J., Vincken, K.L., Viergever, M.A.: Multiscale vessel enhancement filtering. In: Medical Image Computing and Computer-Assisted Intervention—MICCAI’98, pp. 130–137. Springer, Berlin (1998) CrossRefGoogle Scholar
  33. 33.
    Franken, E.: Enhancement of crossing elongated structures in images. Ph.D. thesis, Department of Biomedical Engineering, Eindhoven University of Technology, the Netherlands (2008) Google Scholar
  34. 34.
    Franken, E., Duits, R.: Crossing-preserving coherence-enhancing diffusion on invertible orientation scores. Int. J. Comput. Vis. 85(3), 253–278 (2009). doi: 10.1007/s11263-009-0213-5 CrossRefMathSciNetGoogle Scholar
  35. 35.
    Freeman, W.T., Adelson, E.H.: The design and use of steerable filters. IEEE Trans. Pattern Anal. Mach. Intell. 13, 891–906 (1991) CrossRefGoogle Scholar
  36. 36.
    Führ, H.: Abstract Harmonic Analysis of Continuous Wavelet Transforms. Springer, Berlin (2005) zbMATHGoogle Scholar
  37. 37.
    Granlund, G.H., Knutsson, H.: Signal Processing for Computer Vision. Kluwer Academic, Norwell (1995) CrossRefGoogle Scholar
  38. 38.
    Gregson, P.H., Shen, Z., Scott, R.C., Kozousek, V.: Automated grading of venous beading. Comput. Biomed. Res. 28(4), 291–304 (1995) CrossRefGoogle Scholar
  39. 39.
    Grisan, E., Pesce, A., Giani, A., Foracchia, M., Ruggeri, A.: A new tracking system for the robust extraction of retinal vessel structure. In: 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2004. IEMBS’04, vol. 1, 1620–1623 (2004) Google Scholar
  40. 40.
    Hough, P.: Method and means for recognizing complex patterns. US Patent nr. 3069654, 1962 Google Scholar
  41. 41.
    Hubel, D.H., Wiesel, T.N., Hubel, D., Wiesel, T.: Republication of The Journal of Physiology (1959) 148, 574–591: Receptive fields of single neurones in the cat’s striate cortex. 1959. J. Physiol. (Lond.) 587(Pt 12), 2721–2732 (2009) Google Scholar
  42. 42.
    Johansen, P.: On the classification of toppoints in scale space. J. Math. Imaging Vis. 4(1), 57–67 (1994). doi: 10.1007/BF01250004. CrossRefGoogle Scholar
  43. 43.
    Kalitzin, S.N., Romeny, B.M.T.H., Viergever, M.A.: Invertible apertured orientation filters in image analysis. Int. J. Comput. Vis. 31(2–3), 145–158 (1999). doi: 10.1023/A:1008013815039 CrossRefGoogle Scholar
  44. 44.
    Krause, M., Alles, R., Burgeth, B., Weickert, J.: Fast retinal vessel analysis. J. Real-Time Image Process., 1–10 (2013). doi: 10.1007/s11554-013-0342-5
  45. 45.
    Li, Q., You, J., Zhang, L., Bhattacharya, P.: A multiscale approach to retinal vessel segmentation using Gabor filters and scale multiplication. In: IEEE International Conference on Systems, Man and Cybernetics. SMC’06, vol. 4, pp. 3521–3527 (2006). doi: 10.1109/ICSMC.2006.384665 Google Scholar
  46. 46.
    Lowell, J., Hunter, A., Steel, D., Basu, A., Ryder, R., Kennedy, R.L.: Measurement of retinal vessel widths from fundus images based on 2-D modeling. IEEE Trans. Med. Imaging 23(10), 1196–1204 (2004) CrossRefGoogle Scholar
  47. 47.
    Mumford, D.: Elastica and computer vision. In: Algebraic Geometry and Its Applications, pp. 491–506. Springer, Berlin (1994) CrossRefGoogle Scholar
  48. 48.
    Odstrcilik, J., Jan, J., Kolar, R., Gazarek, J.: Improvement of vessel segmentation by matched filtering in colour retinal images. In: IFMBE Proceeding of World Congress on Medical Physics and Biomedical Engineering, pp. 327–330 (2009) Google Scholar
  49. 49.
    Patton, N., Aslam, T.M., MacGillivray, T., Deary, I.J., Dhillon, B., Eikelboom, R.H., Yogesan, K., Constable, I.J.: Retinal image analysis: concepts, applications and potential. Prog. Retin. Eye Res. 25(1), 99–127 (2006). doi: 10.1016/j.preteyeres.2005.07.001 CrossRefGoogle Scholar
  50. 50.
    Perona, P.: Deformable kernels for early vision. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Proceedings CVPR’91, pp. 222–227 (1991). doi: 10.1109/CVPR.1991.139691 Google Scholar
  51. 51.
    Philipsen, R.: Retinal vascular tree segmentation and classification by means of multiscale vessel filtering and fractal analysis. Master’s thesis, Department of Biomedical Engineering, Eindhoven University of Technology, the Netherlands (2012) Google Scholar
  52. 52.
    Poletti, E., Fiorin, D., Grisan, E., Ruggeri, A.: Automatic vessel segmentation in wide-field retina images of infants with retinopathy of prematurity. Conf Proc IEEE Eng Med Biol Soc 2011, 3954–3957 (2011) Google Scholar
  53. 53.
    Rudin, W.: Functional Analysis. McGraw-Hill Series in Higher Mathematics. McGraw-Hill, New York (1973). W. Rudin—Functional Analysis.djvu zbMATHGoogle Scholar
  54. 54.
    Simoncelli, E.: Design of multi-dimensional derivative filters. In: Proceedings of the IEEE International Conference on Image Processing, ICIP-94, vol. 1, pp. 790–794 (1994). doi: 10.1109/ICIP.1994.413423 Google Scholar
  55. 55.
    Sinthanayothin, C., Boyce, J.F., Cook, H.L., Williamson, T.H.: Automated localisation of the optic disc, fovea, and retinal blood vessels from digital colour fundus images. Br. J. Ophthalmol. 83(8), 902–910 (1999) CrossRefGoogle Scholar
  56. 56.
    Soares, J.V., Leandro, J.J., Cesar Junior, R.M., Jelinek, H.F., Cree, M.J.: Retinal vessel segmentation using the 2-D Gabor wavelet and supervised classification. IEEE Trans. Med. Imaging 25(9), 1214–1222 (2006) CrossRefGoogle Scholar
  57. 57.
    Takahashi, Y., Watanabe, S.: The probability functionals (Onsager-Machlup functions) of diffusion processes. In: Lectures Notes in Mathematics, vol. 851, pp. 433–463. Springer, Berlin (1981) Google Scholar
  58. 58.
    Tasman, W., Jaeger, E.A.: Duane’s ophthalmology. Lippincott Williams and Wilkins (2009).
  59. 59.
    Thornber, K., Williams, L.: Analytic solution of stochastic completion fields. Biol. Cybern. 75, 141–151 (1996) CrossRefzbMATHGoogle Scholar
  60. 60.
    Thornber, K., Williams, L.: Characterizing the distribution of completion shapes with corners using a mixture of random processes. Pattern Recognit. 33, 543–553 (2000) CrossRefGoogle Scholar
  61. 61.
    Weickert, J.: Coherence-enhancing diffusion filtering. Int. J. Comput. Vis. 31(2–3), 111–127 (1999). doi: 10.1023/A:1008009714131 CrossRefGoogle Scholar
  62. 62.
    Wittich, O.: An explicit local uniform large deviation bound for Brownian bridges. Stat. Probab. Lett. 73(1), 51–56 (2005) CrossRefzbMATHMathSciNetGoogle Scholar
  63. 63.
    Wloka, J.: Partial Differential Equations. Cambridge University Press, Cambridge (1987). CrossRefzbMATHGoogle Scholar
  64. 64.
    Xu, X., Niemeijer, M., Song, Q., Sonka, M., Garvin, M.K., Reinhardt, J.M., Abramoff, M.D.: Vessel boundary delineation on fundus images using graph-based approach. IEEE Trans. Med. Imaging 30(6), 1184–1191 (2011) CrossRefGoogle Scholar
  65. 65.
    Yin, Y., Adel, M., Bourennane, S.: Retinal vessel segmentation using a probabilistic tracking method. Pattern Recognit. 45(4), 1235–1244 (2012). doi: 10.1016/j.patcog.2011.09.019 CrossRefzbMATHGoogle Scholar
  66. 66.
    Zhou, L., Rzeszotarski, M.S., Singerman, L.J., Chokreff, J.M.: The detection and quantification of retinopathy using digital angiograms. IEEE Trans. Med. Imaging 13(4), 619–626 (1994) CrossRefGoogle Scholar
  67. 67.
    Zweck, J., Williams, L.R.: Euclidean group invariant computation of stochastic completion fields using shiftable-twistable functions. J. Math. Imaging Vis. 21(2), 135–154 (2004) CrossRefMathSciNetGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2014

Authors and Affiliations

  • Erik Bekkers
    • 1
    Email author
  • Remco Duits
    • 1
  • Tos Berendschot
    • 2
  • Bart ter Haar Romeny
    • 1
  1. 1.Department of Biomedical EngineeringEindhoven University of TechnologyEindhovenThe Netherlands
  2. 2.University Eye Clinic MaastrichtMaastrichtThe Netherlands

Personalised recommendations