Capillary Blood Vessel Tracking Using Polar Coordinates Based Model Identification

  • Mariusz Paradowski
  • Halina Kwasnicka
  • Krzysztof Borysewicz
Part of the Advances in Intelligent and Soft Computing book series (AINSC, volume 57)


Capillaroscopy is one of the best medical diagnostic tools for early detection of scleroderma spectrum disorders. The diagnostic process is based on capillary (small blood vessel) study using a microscope. Key step in capillaroscopy diagnosis is extraction of capillaries. The paper presents a novel semi-automatic method of capillary vessel tracking, which is a non-directional graph creation method. Selection of neighboring vertexes location is its key component. It is performed by model identification. Four capillary model classes are proposed, all using data represented in polar coordinates.


Seed Point Mixed Connective Tissue Disease Direction Curve Automatic Image Annotation Visual Neighborhood 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Mahler, F., Saner, H., Bose, C.: Local cold exposure test for capillaroscopic examination of patients with Raynaud’s syndrome. Microvascular Research 33, 422–427 (1987)CrossRefGoogle Scholar
  2. 2.
    Maricq, M.R.: Raynaud’s phenomen and microvascular abnormalities in scleroderma (systemic sclerisis). Systemic sclerosis, 151–166 (1998)Google Scholar
  3. 3.
    Houtman, P.M., Kallenberg, C.G.M., Fidler, V., et al.: Diagnostic significance of nailfold capillary patterns in patients with Raynaud’s phenomen. Journal of Rheumatology 13, 556–563 (1986)Google Scholar
  4. 4.
    Hoover, A., Kouznetsova, V., Goldbaum, M.: Locating Blood Vessels in Retinal Images by Piece-wise Threshold Probing of a Matched Filter Response. IEEE Transactions on Medical Imaging (2000)Google Scholar
  5. 5.
    Jiang, Y., Bainbridge-Smith, A., Morris, A.B.: Blood Vessel Tracking in Retinal Images. In: Proc. of IVC New Zealand 2007, pp. 126–131 (2007)Google Scholar
  6. 6.
    Boldak, C., Rolland, Y., Toumoulin, C.: An Improved Model-Based Vessel Tracking Algorithm with Application to Computed Tomography Angiography. Biocybernetics And Biomedical Engineering 23(1), 41–63 (2003)Google Scholar
  7. 7.
    Sainthillier, J.-M., Gharbi, T., Muret, P., Humbert, P.: Skin capillary network recognition and analysis by means of neural algorithms. Skin Research and Technology 11, 9–16 (2005)CrossRefGoogle Scholar
  8. 8.
    Condurache, A.P., Aach, T.: Vessel Segmentation in Angiograms using Hysteresis Thresholding. In: Proc. of 9th IAPR, pp. 269–272 (2005)Google Scholar
  9. 9.
    Frangi, A.F., Niessen, W.J., Vincken, K.L., Viergever, M.A.: Multiscale vessel enhancement filtering (1998)Google Scholar
  10. 10.
    Kwasnicka, H., Paradowski, M., Borysewicz, K.: Capillaroscopy Image Analysis as an Automatic Image Annotation Problem. In: Proc. of CISIM 2007, pp. 266–271 (2007)Google Scholar
  11. 11.
    Farzin, H., Abrishami-Moghaddam, H., Moin, M.-S.: A Novel Retinal Identification System. EURASIP Journal on Advances in Signal Processing (2008)Google Scholar
  12. 12.
    Cornea, N.D.: Curve-Skeletons: Properties, Computation and Applications. PhD Thesis, The State University of New Jersey (2007)Google Scholar
  13. 13.
    Kirbas, C., Quek, F.: A Review of Vessel Extraction Techniques and Algorithms. ACM Comput. Surv. 36(2), 81–121 (2004)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Mariusz Paradowski
    • 1
  • Halina Kwasnicka
    • 1
  • Krzysztof Borysewicz
    • 2
  1. 1.Institute of InformaticsWroclaw University of TechnologyPoland
  2. 2.Department of Rheumatology and Internal DiseasesWroclaw Medical UniversityPoland

Personalised recommendations