Advertisement

Hierarchical Discriminative Framework for Detecting Tubular Structures in 3D Images

  • Dirk Breitenreicher
  • Michal Sofka
  • Stefan Britzen
  • Shaohua K. Zhou
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7917)

Abstract

Detecting tubular structures such as airways or vessels in medical images is important for diagnosis and surgical planning. Many state-of-the-art approaches address this problem by starting from the root and progressing towards thinnest tubular structures usually guided by image filtering techniques. These approaches need to be tailored for each application and can fail in noisy or low-contrast regions. In this work, we address these challenges by a two-layer model which consists of a low-level likelihood measure and a high-level measure verifying tubular branches. The algorithm starts by computing a robust measure of tubular presence using a discriminative classifier at multiple image scales. The measure is then used in an efficient multi-scale shortest path algorithm to generate candidate centerline branches and corresponding radii measurements. Finally, the branches are verified by a learning-based indicator function that discards false candidate branches. The experiments on detecting airways in rotational X-ray volumes show that the technique is robust to noise and correctly finds airways even in the presence of imaging artifacts.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Barbu, A., Bogoni, L., Comaniciu, D.: Hierarchical part-based detection of 3D flexible tubes: Application to CT colonoscopy. In: Larsen, R., Nielsen, M., Sporring, J. (eds.) MICCAI 2006. LNCS, vol. 4191, pp. 462–470. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  2. 2.
    Bauer, C., Pock, T., Sorantin, E., Bischof, H., Beichel, R.: Segmentation of interwoven 3D tubular tree structures utilizing shape priors and graph cuts. Med. Image Anal. 14(2), 172–184 (2010)CrossRefGoogle Scholar
  3. 3.
    Benmansour, F., Cohen, L.D.: Tubular structure segmentation based on minimal path method and anisotropic enhancement. Int. J. Comput. Vision 92, 192–210 (2011)CrossRefGoogle Scholar
  4. 4.
    Frangi, A.F., Niessen, W.J., Vincken, K.L., Viergever, M.A.: Multiscale vessel enhancement filtering. In: Wells, W.M., Colchester, A., Delp, S. (eds.) MICCAI 1998. LNCS, vol. 1496, p. 130. Springer, Heidelberg (1998)CrossRefGoogle Scholar
  5. 5.
    Graham, M., Gibbs, J., Cornish, D., Higgins, W.: Robust 3-D airway tree segmentation for image-guided peripheral bronchoscopy. IEEE T. Med. Imaging 29, 982–997 (2010)CrossRefGoogle Scholar
  6. 6.
    Kumar, S., Hebert, M.: A hierarchical field framework for unified context-based classification. In: Proc. Int. Conf. Comput. Vision (2005)Google Scholar
  7. 7.
    Lesage, D., Angelini, E., Bloch, I., Funka-Lea, G.: Design and study of flux-based features for 3D vascular tracking. In: Proc. Int. Symp. Biomed. Imaging (2009)Google Scholar
  8. 8.
    Lesage, D., Angelini, E., Bloch, I., Funka-Lea, G.: A review of 3D vessel lumen segmentation techniques: Models, features and extraction schemes. Med. Image Anal. 13(6), 819–845 (2009)CrossRefGoogle Scholar
  9. 9.
    Lo, P., Sporring, J., Ashraf, H., Pedersen, J.J., de Bruijne, M.: Vessel-guided airway tree segmentation: A voxel classification approach. Med. Image Anal. 14(4), 527–538 (2010)CrossRefGoogle Scholar
  10. 10.
    Ochs, R., Goldin, J., Abtin, F., Kim, H., Brown, K., Batra, P., Roback, D., McNitt-Gray, M., Brown, M.: Automated classification of lung bronchovascular anatomy in CT using AdaBoost. Med. Image Anal. 11, 315–324 (2007)CrossRefGoogle Scholar
  11. 11.
    Palágyi, K., Sorantin, E., Balogh, E., Kuba, A., Halmai, C., Erdohelyi, B., Hausegger, K.: A sequential 3D thinning algorithm and its medical applications. In: Insana, M.F., Leahy, R.M. (eds.) IPMI 2001. LNCS, vol. 2082, pp. 409–415. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  12. 12.
    Rouchdy, Y., Cohen, L.: A geodesic voting method for the segmentation of tubular tree and centerlines. In: Proc. Int. Symp. on Biomed. Imaging, pp. 979–983 (2011)Google Scholar
  13. 13.
    Schuh, A., Kaftan, J.N., Tietjen, C., O’Donnell, T.P.: Sparse axes-aligned MFlux. In: Workshop on Comp. and Vis. for (Intra-) Vascular Imaging (2011)Google Scholar
  14. 14.
    Sofka, M., Zhang, J., Zhou, S., Comaniciu, D.: Multiple object detection by sequential Monte Carlo and hierarchical detection network. In: Proc. Int. Conf. Comput. Vision and Pattern Recogn., San Francisco, CA, June 13-18 (2010)Google Scholar
  15. 15.
    Steger, T., Hosbach, M.: Navigated bronchoscopy using intraoperative fluoroscopy and preoperative CT. In: Proc. Int. Symp. on Biomed. Imaging, pp. 1220–1223 (2012)Google Scholar
  16. 16.
    Tu, Z.: Probabilistic boosting-tree: learning discriminative models for classification, recognition, and clustering. In: Proc. Int. Conf. Comput. Vision (2005)Google Scholar
  17. 17.
    Tu, Z., Bai, X.: Auto-context and its application to high-level vision tasks and 3D brain image segmentation. IEEE Trans. Pattern Anal. Machine Intelligence 32, 1744–1757 (2010)CrossRefGoogle Scholar
  18. 18.
    Türetken, E., Benmansour, F., Fua, P.: Automated reconstruction of tree structures using path classifiers and mixed integer programming. In: Proc. Int. Conf. Comput. Vision and Pattern Recogn., pp. 566–573. IEEE (2012)Google Scholar
  19. 19.
    Wolf, L., Bileschi, S.: A critical view of context. Int. J. Comput. Vision (2006)Google Scholar
  20. 20.
    Zheng, Y., Loziczonek, M., Georgescu, B., Zhou, S.K., Vega-Higuera, F., Comaniciu, D.: Machine learning based vesselness measurement for coronary artery segmentation in cardiac CT volumes. In: Proc. SPIE (2011)Google Scholar
  21. 21.
    Zhou, J., Chang, S., Metaxas, D., Axel, L.: Vascular structure segmentation and bifurcation detection. In: Proc. Int. Symp. on Biomed. Imaging, pp. 872–875 (2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Dirk Breitenreicher
    • 1
  • Michal Sofka
    • 1
  • Stefan Britzen
    • 2
  • Shaohua K. Zhou
    • 1
  1. 1.Imaging and Computer VisionSiemens Corporation, Corporate TechnologyPrincetonUSA
  2. 2.Imaging & Therapy SystemsSiemens HealthcareForchheimGermany

Personalised recommendations