Globally-Optimal Anatomical Tree Extraction from 3D Medical Images Using Pictorial Structures and Minimal Paths

  • Zahra MirikharajiEmail author
  • Mengliu Zhao
  • Ghassan Hamarneh
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10434)


Extracting centerlines of anatomical trees (e.g., vasculature and airways) from 3D medical images is a crucial preliminary step for various medical applications. We propose an automatic tree extraction method that leverages prior knowledge of tree topology and geometry and ensures globally-optimal solutions. We define a pictorial structure with a corresponding cost function to detect tree bifurcations in anatomical trees with predefined topology. The tree bifurcations are encoded as nodes in the pictorial structure and are associated with an artificial neural network (ANN) based unary term. The geometrical (direction and length) statistics of tree branches are learned from a training set and encoded as geometrical priors for regularizing the pictorial structure edges. Finally, detected bifurcations as well as the ANN tubularity scores, are leveraged to trace globally optimal minimal paths along 3D tree centrelines. Our method outperforms competing state-of-the-art when evaluated on 3D synthesized vasculature and lung airways in CT and our results demonstrate the advantages of incorporating tree statistics and global optimization for this task.


Tree-like Pictorial structure Geometrical prior Bifurcation detection Centerline extraction Global optimization 



Thanks to the Natural Sciences and Engineering Research Council (NSERC) of Canada for partially funding this work.


  1. 1.
    Belagiannis, et al.: 3D pictorial structures for multiple human pose estimation. In: CVPR, pp. 1669–1676 (2014)Google Scholar
  2. 2.
    Bériault, S., et al.: Automatic SWI venography segmentation using conditional random fields. IEEE TMI 34(12), 2478–2491 (2015)Google Scholar
  3. 3.
    Burenius, M., et al.: 3D pictorial structures for multiple view articulated pose estimation. In: CVPR, pp. 3618–3625 (2013)Google Scholar
  4. 4.
    Deschamps, T.: Curve and shape extraction with minimal path an level-sets techniques: applications to 3D Medical Imaging. Ph.D. thesis, University of Paris Dauphine (2001)Google Scholar
  5. 5.
    Felzenszwalb, P.F., et al.: Pictorial structures for object recognition. IJCV 61(1), 55–79 (2005)CrossRefGoogle Scholar
  6. 6.
    Felzenszwalb, P., Huttenlocher, D.: Distance transforms of sampled functions. Cornell University, Technical report (2004)Google Scholar
  7. 7.
    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, pp. 130–137. Springer, Heidelberg (1998). doi: 10.1007/BFb0056195CrossRefGoogle Scholar
  8. 8.
    Hinton, G.E., et al.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504–507 (2006)MathSciNetCrossRefGoogle Scholar
  9. 9.
    Krissian, K., et al.: A minimal cost path and level set evolution approach for carotid bifurcation segmentation. Midas J. (2009)Google Scholar
  10. 10.
    Law, M.W.K., Chung, A.C.S.: Three dimensional curvilinear structure detection using optimally oriented flux. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008. LNCS, vol. 5305, pp. 368–382. Springer, Heidelberg (2008). doi: 10.1007/978-3-540-88693-8_27CrossRefGoogle Scholar
  11. 11.
    Lesage, D., et al.: Adaptive particle filtering for coronary artery segmentation from 3D CT angiograms. CVIU 151, 29–46 (2016)Google Scholar
  12. 12.
    Li, H., Yezzi, A.: Vessels as 4D curves: Global minimal 4D paths to extract 3D tubular surfaces and centerlines. IEEE TMI 26(9), 1213–1223 (2007)Google Scholar
  13. 13.
    Macedo, et al.: A centerline-based estimator of vessel bifurcations in angiography images. In: SPIE Medical Imaging, p. 86703K (2013)Google Scholar
  14. 14.
    Metz, C., et al.: Two point minimum cost path approach for CTA coronary centerline extraction. Insight J., 123 (2008)Google Scholar
  15. 15.
    M’hiri, F., et al.: A graph-based approach for spatio-temporal segmentation of coronary arteries in X-ray angiographic sequences. Comput. Biol. Med. 79, 45–58 (2016)CrossRefGoogle Scholar
  16. 16.
    Mueller, D.: Fast marching minimal path extraction in ITK. Insight J., 1–8 (2008)Google Scholar
  17. 17.
    Nosrati, et al.: Incorporating prior knowledge in medical image segmentation: a survey. CoRR abs/1607.01092 (2016).
  18. 18.
    Prim, R.C., et al.: Shortest connection networks and some generalizations. Bell Labs Tech. J. 36(6), 1389–1401 (1957)CrossRefGoogle Scholar
  19. 19.
    Rempfler, M., et al.: Extracting vascular networks under physiological constraints via integer programming. In: Golland, P., Hata, N., Barillot, C., Hornegger, J., Howe, R. (eds.) MICCAI 2014. LNCS, vol. 8674, pp. 505–512. Springer, Cham (2014). doi: 10.1007/978-3-319-10470-6_63CrossRefGoogle Scholar
  20. 20.
    Robben, D., Türetken, E., Sunaert, S., Thijs, V., Wilms, G., Fua, P., Maes, F., Suetens, P.: Simultaneous segmentation and anatomical labeling of the cerebral vasculature. In: Golland, P., Hata, N., Barillot, C., Hornegger, J., Howe, R. (eds.) MICCAI 2014. LNCS, vol. 8673, pp. 307–314. Springer, Cham (2014). doi: 10.1007/978-3-319-10404-1_39CrossRefGoogle Scholar
  21. 21.
    Schaap, M., et al.: Standardized evaluation methodology and reference database for evaluating coronary artery centerline extraction algorithms. MIA 13(5), 701–714 (2009)Google Scholar
  22. 22.
    Schneider, M., et al.: Joint 3D vessel segmentation and centerline extraction using oblique Hough forests with steerable filters. MIA 19(1), 220–249 (2015)Google Scholar
  23. 23.
    Skibbe, H., et al.: Efficient Monte Carlo image analysis for the location of vascular entity. IEEE TMI 34(2), 628–643 (2015)Google Scholar
  24. 24.
    Türetken, E., et al.: Automated reconstruction of dendritic and axonal trees by global optimization with geometric priors. Neuroinformatics 9(2–3), 279–302 (2011)CrossRefGoogle Scholar
  25. 25.
    Türetken, E., et al.: Automated reconstruction of tree structures using path classifiers and mixed integer programming. In: CVPR, pp. 566–573. IEEE (2012)Google Scholar
  26. 26.
    Wu, A., et al.: Deep vessel tracking: a generalized probabilistic approach via deep learning. In: IEEE ISBI, pp. 1363–1367 (2016)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Zahra Mirikharaji
    • 1
    Email author
  • Mengliu Zhao
    • 1
  • Ghassan Hamarneh
    • 1
  1. 1.Medical Image Analysis LabSimon Fraser UniversityBurnabyCanada

Personalised recommendations