In this paper, we present a novel method for extracting center axis representations (centerlines) of blood vessels in contrast enhanced (CE)-CTA/MRA, robustly and accurately. This graph-based optimization algorithm which employs multi-scale medialness filters extracts vessel centerlines by computing the minimum-cost paths. Specifically, first, new medialness filters are designed from the assumption of circular/elliptic vessel cross-sections. These filters produce contrast and scale independent responses even the presence of nearby structures. Second, they are incorporated to the minimum-cost path detection algorithm in a novel way for the computational efficiency and accuracy. Third, the full vessel centerline tree is constructed from this optimization technique by assigning a saliency measure for each centerline from their length and radius information. The proposed method is computationally efficient and produces results that are comparable in quality to the ones created by experts. It has been tested on more than 100 coronary artery data set where the full coronary artery trees are extracted in 21 seconds in average on a 3.2GHz PC.

Supplementary material (13.8 mb)
Supplementary Material (14,167 KB) (5.8 mb)
Supplementary Material (5,927 KB)


  1. 1.
    Aylward, S., Eberly, E.: Initialization, noise, singularities, and scale in height-ridge traversal for tubular object centerline extraction. TMI 21(2), 61–75 (2002)Google Scholar
  2. 2.
    Aylward, S., Pizer, S., Bullitt, E., Eberly, D.: Intensity ridge and widths for 3d object segmentation and description. In: IEEE Proc. Workshop MMBIA, pp. 131–138 (1996)Google Scholar
  3. 3.
    Deschamps, T., Cohen, L.: Fast extraction of minimal paths in 3d images and applications to virtual endoscopy. Medical Image Analysis 5(4), 281–299 (2001)CrossRefGoogle Scholar
  4. 4.
    Dijkstra, E.W.: A note on two problems in connections with graphs. Numerische Mathematic 1, 269–271 (1959)zbMATHCrossRefMathSciNetGoogle Scholar
  5. 5.
    Frangi, A.F., Niessen, W.J., Vincken, K.L., Viergever, M.A.: Multiscale vessel enhancement filtering. In: Wells, W.M., Colchester, A.C.F., Delp, S.L. (eds.) MICCAI 1998. LNCS, vol. 1496, pp. 82–89. Springer, Heidelberg (1998)Google Scholar
  6. 6.
    Koller, T.M., Gerig, G., Szekely, G., Dettwiler, D.: Multiscale detection of curvilinear structures in 2-D and 3-D image data. In: ICCV, pp. 864–869 (1995)Google Scholar
  7. 7.
    Krissian, K., Malandain, G., Ayache, N., Vaillant, R., Trousset, Y.: Model based multiscale detection of 3D vessels. In: IEEE Conf. CVPR, pp. 722–727 (1998)Google Scholar
  8. 8.
    Li, H., Yezzi, A.J.: Vessels as 4-D curves: Global minimal 4-D paths to extract 3-D tubular surfaces and centerlines. IEEE Trans. Med. Imaging 26(9), 1213–1223 (2007)CrossRefGoogle Scholar
  9. 9.
    Sethian, J.A.: Level Set Methods. Cambridge University Press, New York (1996)zbMATHGoogle Scholar
  10. 10.
    Siddiqi, K., Vasilevskiy, A.: 3D flux maximizing flows. In: International Workshop on Energy Minimizing Methods In Computer Vision (2001)Google Scholar
  11. 11.
    Tyrrell, J.A., di Tomaso, E., Fuja, D., Tong, R., Kozak, K., Brown, E.B., Jain, R., Roysam, B.: Robust 3-D modeling of vasculature imagery using superellipsoids. IEEE Transactions on Medical Imaging (2006)Google Scholar
  12. 12.
    Wink, O., Niessen, W.J., Viergever, M.A.: Multiscale vessel tracking. IEEE Trans. on Medical Imaging 23(1), 130–133 (2004)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • M. Akif Gülsün
    • 1
  • Hüseyin Tek
    • 1
  1. 1.Imaging and VisualizationSiemens Corporate ResearchPrincetonUSA

Personalised recommendations