Advertisement

Monte Carlo Sampling for the Segmentation of Tubular Structures

Abstract

In this paper, we present a multiple hypotheses testing for the segmentation of tubular structures in medical imaging that addresses appearance (scanner artifacts, pathologies,…) and geometric (bifurcations) non-linearities. Our method represents vessels/tubular structures as sequences of state vectors (vessel cuts/cross-sections), which are described by the position of the corresponding plane, the center of the vessel in this plane and its radius. Thus, 3D segmentation consists in finding the optimal sequence of 2D planes normal to the vessel’s centerline. This sequence of planes is modeled by a probability density function (pdf for short) which is maximized with respect to the parameters of the state vector. Such a pdf is approximated in a non-parametric way, the Particle Filter approach, that is able to express multiple hypotheses (branches). Validation using ground truth from clinical experts and very promising experimental results for the segmentation of the coronaries demonstrates the potential of the proposed approach.

Keywords

Particle Filter Front Propagation Deformable Model Vessel Segmentation Vessel Cross Section 
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.

References

  1. 1.
    S. Arulampalam, S. Maskell, N. Gordon, and T. Clapp. A Tutorial on Particle Filters for On-line Non-linear/Non-Gaussian Bayesian Tracking. IEEE Trans. on Signal Process., 50:174–188, 2002.CrossRefGoogle Scholar
  2. 2.
    B. Avants and J. Williams. An adaptive minimal path generation technique for vessel tracking in CTA/CE-MRA volume images. In Med. Image Comput. Comput. Assist. Interv. Int. Conf., volume 3749, pages 707–716. Springer, 2000.Google Scholar
  3. 3.
    S. Bouix, K. Siddiqi, and A. R. Tannenbaum. Flux driven automatic centerline extraction. In Med. Image Anal., volume 9, pages 209–221(3), 2005.CrossRefGoogle Scholar
  4. 4.
    V. Caselles, F. Catté, B. Coll, and F. Dibos. A geometric model for active contours in image processing. Numerische Mathematik, 66(1):1–31, 1993.CrossRefMATHMathSciNetGoogle Scholar
  5. 5.
    T. Deschamps. Curve and Shape Extraction with Minimal Path and Level-Sets techniques-Applications to 3D Medical Imaging. PhD thesis, Université Paris-IX Dauphine, Place du maréchal de Lattre de Tassigny, 75775 Paris Cedex, Dec. 2001.Google Scholar
  6. 6.
    T. Deschamps and L. Cohen. Fast extraction of tubular and tree 3d surfaces with front propagation methods. In IARP International Conference on Pattern Recognition, volume 1, pages 731–734. IEEE Computer Society, 2002.Google Scholar
  7. 7.
    T. Deschamps and L. D. Cohen. Fast extraction of minimal paths in 3D images and applications to virtual endoscopy. Med. Image Anal., 5(4):281–299, Dec. 2001.CrossRefGoogle Scholar
  8. 8.
    A. Doucet, J. de Freitas, and N. Gordon. Sequential Monte Carlo Methods in Practice. Springer-Verlag, New York, 2001.Google Scholar
  9. 9.
    A. Doucet, N. Gordon, and C. Andrieu. On Sequential Monte Carlo Sampling Methods for Bayesian Filtering. Statistics and Computing, 10(3):197–208, 2000.CrossRefGoogle Scholar
  10. 10.
    R. Duda and P. Hart. Pattern Classification and Scene Analysis. John Wiley and Sons, 1973.MATHGoogle Scholar
  11. 11.
    M. Figueiredo and J. Leitao. A nonsmoothing approach to the estimation of vessel contours in angiograms. IEEE Trans. Med. Imaging, 14:162–172, 1995.CrossRefGoogle Scholar
  12. 12.
    C. Florin, N. Paragios, and J. Williams. Particle filters, a Quasi-Monte Carlo solution for segmentation of coronaries. In Med. Image Comput. Comput. Assist. Interv. Int. Conf., pages 246–253, 2005.Google Scholar
  13. 13.
    C. Florin, N. Paragios, and J. Williams. Globally optimal active contours, sequential monte carlo and on-line learning for vessel segmentation. In European Conference on Computer Vision, volume 3953, pages 476–489, 2006.Google Scholar
  14. 14.
    A. Frangi, W. Niessen, P. Nederkoorn, O. Elgersma, and M. Viergever. Three-dimensional model-based stenosis quantification of the carotid arteries from contrast-enhanced MR angiography. In IEEE Mathematical Methods in Biomedical Image Analysis, pages 110–118, 2000.Google Scholar
  15. 15.
    A. F. Frangi, W. J. Niessen, K. L. Vincken, and M. A. Viergever. Multiscale vessel enhancement filtering. Lecture Notes in Computer Science, 1496, 1998.Google Scholar
  16. 16.
    N. Gordon. Novel Approach to Nonlinear/Non-Gaussian Bayesian State Estimation. IEEE Proceedings, 140:107–113, 1993.Google Scholar
  17. 17.
    M. Hart and L. Holley. A method of Automated Coronary Artery Tracking in Unsubtracted Angiograms. IEEE Comput. in Cardiol., pages 93–96, 1993.Google Scholar
  18. 18.
    M. Isard and A. Blake. Contour Tracking by Stochastic Propagation of Conditional Density. In European Conference on Computer Vision, volume I, pages 343–356,1996.Google Scholar
  19. 19.
    K. Krissian, G. Malandain, N. Ayache, R. Vaillant, and Y. Trousset. Model based detection of tubular structures in 3d images. Computer Vision and Image Understanding, 80:130–171, 2000.CrossRefMATHGoogle Scholar
  20. 20.
    L. Lorigo, O. Faugeras, E. Grimson, R. Keriven, R. Kikinis, A. Nabavi, and C. Westin. Codimension-Two Geodesic Active Controus for the Segmentation of Tubular Structures. In IEEE Conference on Computer Vision and Pattern Recognition, pages I:444–451, 2000.Google Scholar
  21. 21.
    R. Malladi and J. Sethian. A Real-Time Algorithm for Medical Shape Recovery. In IEEE International Conference in Computer Vision, pages 304–310, 1998.Google Scholar
  22. 22.
    D. Nain, A. Yezzi, and G. Turk. Vessel Segmentation Using a Shape Driven Flow. In Med. Image Comput. Comput. Assist. Interv. Int. Conf., 1, pages 51–59. Springer, 2004.Google Scholar
  23. 23.
    T. O´ Donnell, T. Boult, X. Fang, and A. Gupta. The Extruded Generalized Cylider: A Deformable Model for Object Recovery. In IEEE Conference on Computer Vision and Pattern Recognition, pages 174–181, 1994.Google Scholar
  24. 24.
    S. Osher and N. Paragios. Geometric Level Set Methods in Imaging, Vision and Graphics. Springer Verlag, 2003.MATHGoogle Scholar
  25. 25.
    R. Petrocelli, K. Manbeck, and J. Elion. Three Dimensional Structure Recognition in Digital Angiograms using Gauss-Markov Models. In Comput. in Radiol., pages 101–104. IEEE, 1993.Google Scholar
  26. 26.
    F. L. Ruberg. Computed Tomography of the Coronary Arteries. London, UK: Taylor & Francis, 2005.CrossRefGoogle Scholar
  27. 27.
    D. Rueckert, P. Burger, S. Forbat, R. Mohiadin, and G. Yang. Automatic Tracking of the Aorta in Cardiovascular MR images using Deformable Models. IEEE Trans. Med. Imaging, 16: 581–590, 1997.CrossRefGoogle Scholar
  28. 28.
    J. Sethian. A Review of the Theory, Algorithms, and Applications of Level Set Methods for Propagating Interfaces. Cambridge University Press, pages 487–499, 1995.Google Scholar
  29. 29.
    J. Sethian. Level Set Methods. Cambridge University Press, 1996.MATHGoogle Scholar
  30. 30.
    M. Sofka and C. V. Stewart. Retinal vessel extraction using multiscale matched filters, confidence and edge measures. IEEE Trans. Med. Imaging, 25(12):1531–1546, 2006.CrossRefGoogle Scholar
  31. 31.
    E. Sorantin, C. Halmai, B. Erbohelyi, K. Palagyi, K. Nyul, K. Olle, B. Geiger, F. Lindbichler, G. Friedrich, and K. Kiesler. Spiral-CT-based assessment of Tracheal Stenoses using 3D Skeletonization. IEEE Trans. Med. Imaging, 21:263–273, 2002.CrossRefGoogle Scholar
  32. 32.
    K. Toyama and A. Blake. Probabilistic Tracking in a Metric Space. In IEEE International Conference in Computer Vision, pages 50–59, 2001.Google Scholar
  33. 33.
    J. Tsitsiklis. Efficient Algorithms for Globally Optimal Trajectories. IEEE Transactions on Automatic Control, 40:1528–1538, 1995.CrossRefMATHMathSciNetGoogle Scholar
  34. 34.
    W. West. Modeling with mixtures. In J. Bernardo, J. Berger, A. Dawid, and A. Smith, editors, Bayesian Statistics 4. Clarendon Press, 1993.Google Scholar
  35. 35.
    O. Wink, W. J. Niessen, and M. A. Viergever. Multiscale vessel tracking. IEEE Trans. Med. Imaging, 23(1):130–133, 2004.CrossRefGoogle Scholar
  36. 36.
    S. Y., N. S., S. N., A. H., Y. S., K. T., G. G., and K. R. Three-dimensional multi-scale line filter for segmentation and visualization of curvilinear structures in medical images. Med. Image Anal., 2:143–168(26), 1998.Google Scholar
  37. 37.
    P. Yim, P. Choyke, and R. Summers. Grayscale Skeletonization of Small Vessels in Magnetic Resonance Angiography. IEEE Trans. Med. Imaging, 19:568–576, 2000.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2015

Authors and Affiliations

  1. 1.Corporate TechnologySiemens CorporationPrincetonUSA
  2. 2.Center for Visual Computing, Department of Applied MathematicsEcole Centrale ParisParisFrance
  3. 3.CEO at Siemens Healthcare Molecular Imaging, Siemens HealthcareNürnbergUSA

Personalised recommendations