Accurate and Robust Fully-Automatic QCA: Method and Numerical Validation

  • Antonio Hernández-Vela
  • Carlo Gatta
  • Sergio Escalera
  • Laura Igual
  • Victoria Martin-Yuste
  • Petia Radeva
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6893)

Abstract

The Quantitative Coronary Angiography (QCA) is a methodology used to evaluate the arterial diseases and, in particular, the degree of stenosis. In this paper we propose AQCA, a fully automatic method for vessel segmentation based on graph cut theory. Vesselness, geodesic paths and a new multi-scale edgeness map are used to compute a globally optimal artery segmentation. We evaluate the method performance in a rigorous numerical way on two datasets. The method can detect an artery with precision 92.9 ±5% and sensitivity 94.2 ±6%. The average absolute distance error between detected and ground truth centerline is 1.13 ±0.11 pixels (about 0.27±0.025mm) and the absolute relative error in the vessel caliber estimation is 2.93% with almost no bias. Moreover, the method can discriminate between arteries and catheter with an accuracy of 96.4%.

Keywords

Vessel segmentation centerline extraction QCA GraphCut 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Benmansour, F., Cohen, L.: Tubular structure segmentation based on minimal path method and anisotropic enhancement, vol. 92, pp. 192–210. Springer, Netherlands (2011)Google Scholar
  2. 2.
    Boykov, Y., Funka-Lea, G.: Graph cuts and efficient n-d image segmentation, vol. 70, pp. 109–131. Kluwer Academic Publishers, Hingham (2006)Google Scholar
  3. 3.
    Boykov, Y., Kolmogorov, V.: An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision, vol. 26, pp. 359–374. IEEE Computer Society, Los Alamitos (2001)MATHGoogle Scholar
  4. 4.
    Candemir, S., Akgul, Y.: Adaptive regularization parameter for graph cut segmentation. In: Campilho, A., Kamel, M. (eds.) ICIAR 2010. LNCS, vol. 6111, pp. I:117–I:126. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  5. 5.
    Fallavollita, P., Cheriet, F.: Towards an automatic coronary artery segmentation algorithm. In: EMBS 2006, pp. 3037–3040. IEEE Computer Society, Los Alamitos (August 2006)Google Scholar
  6. 6.
    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. 130–137. Springer, Heidelberg (1998)CrossRefGoogle Scholar
  7. 7.
    Kirbas, C., Quek, F.: A review of vessel extraction techniques and algorithms, vol. 36, pp. 81–121. ACM, New York (2004)Google Scholar
  8. 8.
    Kolmogorov, V., Zabih, R.: What energy functions can be minimized via graph cuts, vol. 26, pp. 65–81. IEEE Computer Society, Los Alamitos (2004)MATHGoogle Scholar
  9. 9.
    Lopez, A.M., Lumbreras, F., Serrat, J., Villanueva, J.J.: Evaluation of methods for ridge and valley detection, vol. 21, pp. 327–335. IEEE Computer Society, Los Alamitos (1999)Google Scholar
  10. 10.
    Mirzaalian, H., Hamarneh, G.: Vessel scale-selection using mrf optimization. In: CVPR, pp. 3273–3279. IEEE Computer Society, Los Alamitos (June 2010)Google Scholar
  11. 11.
    Schaap, M., van Walsum, T., Niessen, W.: Standardized evaluation methodology and reference database for evaluating coronary artery centerline extraction algorithms, vol. 13, pp. 701–714. Elsevier, Amsterdam (2009)Google Scholar
  12. 12.
    Schneider, M., Sundar, H.: Automatic global vessel segmentation and catheter removal using local geometry information and vector field integration. In: IEEE ISBI, pp. 45–48. IEEE Press, Los Alamitos (2010)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Antonio Hernández-Vela
    • 1
    • 2
  • Carlo Gatta
    • 1
    • 2
  • Sergio Escalera
    • 1
    • 2
  • Laura Igual
    • 1
    • 2
  • Victoria Martin-Yuste
    • 3
  • Petia Radeva
    • 1
    • 2
  1. 1.Dept. MAIAUniversitat de BarcelonaBarcelonaSpain
  2. 2.Centre de Visió per ComputadorEdifici O, Campus UABBellaterraSpain
  3. 3.Institut Clinic del ToraxHospital Clinic BarcelonaBarcelonaSpain

Personalised recommendations