Anisotropic Haralick Edge Detection Scheme with Application to Vessel Segmentation

  • Ali Gooya
  • Takeyoshi Dohi
  • Ichiro Sakuma
  • Hongen Liao
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5128)


In this paper, detection of edges in oriented fields is addressed. Haralick edge detection is an accurate scheme for estimation of the edge in a Euclidean space. However, in some applications such as edge detection for vessel segmentation because of the intrinsic orientation of structures, accuracy is only demanded in a particular subspace. This is specially usefull when a curve evolution is chosen for segmentation since gradients in parallel to vessel orientation stops evolution. Haralick edge detection is generalized on a Riemannian space using the inner product of the vectors under a space metric tensor. This eliminates the spurious gradients and preserves the accuracy on the vessel border. Examples are given and the comparison is made with the state-of-the-art flux maximizing flow indicating that significant improvements in terms of leakage minimization and thiner vessel delineation is achievable using our methodology.


Magnetic Resonance Angiography Edge Detection Active Contour Riemannian Space Curve Evolution 
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.
    Lorgio, L.M., Faugeras, O.D., Grimson, W.E.L., Kerivan, R., Kikinis, R., Nabavai, A., Westin, C.F.: CURVES: Curve evolution for vessel segmentation. Medical Image Analysis 5, 195–206 (2001)CrossRefGoogle Scholar
  2. 2.
    Yan, P., Kassim, A.A.: Segmentation of volumetric MRA images by using capillary active contour. Medical Image Analysis 10(3), 317–329 (2006)CrossRefGoogle Scholar
  3. 3.
    Vasilevsky, A., Siddiqi, K.: Flux maximizing geometric flows. IEEE Trans. Pat. Anal. Mach. Intel. 24(12), 1565–1578 (2002)CrossRefGoogle Scholar
  4. 4.
    Gazit, M.H., Kimmel, R., Peled, N., Goldsher, D.: Segmentation of thin structures in volumetric medical images. IEEE Trans. Image Proc. 15(2), 354–363 (2006)CrossRefGoogle Scholar
  5. 5.
    Caselles, V., Kimmel, R., Sapiro, G.: Geodesic Active Contours. Int. Journal of Computer Vision 22(1), 61–79 (1997)zbMATHCrossRefGoogle Scholar
  6. 6.
    Shah, J.: Riemannian Drums, Anisotropic Curve Evolution and Segmentation. In: Nielsen, M., Johansen, P., Fogh Olsen, O., Weickert, J. (eds.) Scale-Space 1999. LNCS, vol. 1682, pp. 129–140. Springer, Heidelberg (1999)CrossRefGoogle Scholar
  7. 7.
    Zaho, H.K., Chan, T., Merriman, B., Osher, S.: A variational level set approach to multiphase motion. Journal of Computational Physics 127, 179–195 (1996)CrossRefMathSciNetGoogle Scholar
  8. 8.
    Chan, T.F., Vese, A.: Active contours without edges. IEEE Trans. Imag. Proc. 10, 266–277 (2001)zbMATHCrossRefGoogle Scholar
  9. 9.
    Agam, G., Armato, S., Wu, C.: Vessel Tree Reconstruction in Thoracic CT Scans With Application to Nodule Detection. IEEE Trans. Imag. Proc. 24(4), 486–499 (2005)Google Scholar
  10. 10.
    Haralick, R.: Digital step edge from zero crossing of second directional derivatives. IEEE Trans. Patt. Rec. Mach. Vis. 1(1), 58–68 (1984)Google Scholar
  11. 11.
    John Canny, F.: A Computational Approach to Edge Detection. IEEE Trans. Patt. Rec. Mach. Vis. 8, 679–698 (1986)Google Scholar
  12. 12.
    Marr, D., Hildreth, E.: Theory of Edge Detection, A Computational Approach to Edge Detection. Proc. Roy. Soc. Lond. B 207, 187–217 (1980)Google Scholar
  13. 13.
    Law, M.W.K., CHung, A.C.S.: Weighted local variance-based edge detection and its application to vascular segmentation in Magnetic Resonance Angiography. IEEE Trans. Imag. Proc. 26(9), 1224–1241 (2007)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Ali Gooya
    • 1
  • Takeyoshi Dohi
    • 2
  • Ichiro Sakuma
    • 1
  • Hongen Liao
    • 1
    • 3
  1. 1.Graduate School of EngineeringThe University of Tokyo 
  2. 2.Graduate School of Informaiton Science and TechnologyThe University of Tokyo 
  3. 3.Translational Systems Biology and Medicine InitiativeThe University of TokyoTokyo 

Personalised recommendations