Hierarchical Markov Random Fields Applied to Model Soft Tissue Deformations on Graphics Hardware

  • Christof Seiler
  • Philippe Büchler
  • Lutz-Peter Nolte
  • Mauricio Reyes
  • Rasmus Paulsen
Chapter

Abstract

Many methodologies dealing with prediction or simulation of soft tissue deformations on medical image data require preprocessing of the data in order to produce a different shape representation that complies with standard methodologies, such as mass–spring networks, finite element methods (FEM). On the other hand, methodologies working directly on the image space normally do not take into account mechanical behavior of tissues and tend to lack physics foundations driving soft tissue deformations. This chapter presents a method to simulate soft tissue deformations based on coupled concepts from image analysis and mechanics theory. The proposed methodology is based on a robust stochastic approach that takes into account material properties retrieved directly from the image, concepts from continuum mechanics and FEM. The optimization framework is solved within a hierarchical Markov random field (HMRF) which is implemented on the graphics processor unit (GPU).

References

  1. 1.
    Bachtar F, Chen X, Hisada T (2006) Finite element contact analysis of the hip joint. Medical and Biological Engineering and Computing 44(8):643–651CrossRefGoogle Scholar
  2. 2.
    Boyd SK, Müller R (2006) Smooth surface meshing for automated finite element model generation from 3D image data. Journal of Biomechanics 39(7):1287–1295CrossRefGoogle Scholar
  3. 3.
    Carreras IA, Sorzano C, Marabini R, Carazo J, De Solorzano CO, Kybic J (2006) Consistent and Elastic Registration of Histological Sections Using Vector-Spline Regularization. Computer Vision Approaches to Medical Image Analysis, pp. 85–95Google Scholar
  4. 4.
    Geman D (1990) Random Fields and Inverse Problems in Imaging. In: Saint-Flour Lectures 1988, Lecture Notes in Mathematics, pp. 113–193Google Scholar
  5. 5.
    Geman S, Geman D (1984) Stochastic relaxation, Gibbs distributions and the Bayesian restoration of images. IEEE Transactions on Pattern Analysis and Machine Intelligence 6(6): 721–741MATHCrossRefGoogle Scholar
  6. 6.
    Göddeke D (2005) GPGPU Basic Math Tutorial. Technical report, FB Mathematik, Universität DortmundGoogle Scholar
  7. 7.
    Green S (2005) The OpenGL Framebuffer Object Extension. NVIDIA Corporation, GDCGoogle Scholar
  8. 8.
    Gummaraju J, Rosenblum M (2005) Stream Programming on General-Purpose Processors. In: Proceedings of the 38th annual IEEE/ACM International Symposium on Microarchitecture, Barcelona, SpainGoogle Scholar
  9. 9.
    Jodoin PM, Mignotte M (2006) Markovian segmentation and parameter estimation on graphics hardware. Journal of Electronic Imaging 15(3):033005-1–033005-15Google Scholar
  10. 10.
    Jodoin PM, St Amour JF, Mignotte M (2005) Unsupervised Markovian segmentation on graphics hardware. Pattern Recognition and Image Analysis 3687:444–454CrossRefGoogle Scholar
  11. 11.
    Mohamed A, Zacharaki EI, Shen D, Davatzikos C (2006) Deformable registration of brain tumor images via a statistical model of tumor-induced deformation. Medical Image Analysis 10(5):752–763CrossRefGoogle Scholar
  12. 12.
    Murino V, Castellani U, Fusiello A (2001) Disparity map restoration by integration of confidence in Markov random fields models. In: International Conference on Image ProcessingGoogle Scholar
  13. 13.
    Paulsen RR (2004) Statistical Shape Analysis of the Human Ear Canal with Application to In-the-Ear Hearing Aid Design. PhD thesis, Technical University of DenmarkGoogle Scholar
  14. 14.
    Provost JN, Collet C, Rostaing P, Pérez P, Bouthemy P (2004) Hierarchical Markovian segmentation of multispectral images for the reconstruction of water depth maps. Computer Vision and Image Understanding 93(2):155–174CrossRefGoogle Scholar
  15. 15.
    de Putter S, van de Vosse FN, Gerritsen, FA, Laffargue F, Breeuwer M (2006) Computational mesh generation for vascular structures with deformable surfaces. International Journal of Computer Assisted Radiology and Surgery 1(1):39–49CrossRefGoogle Scholar
  16. 16.
    Rueckert D, Sonoda LI, Hayes C, Hill DLG, Leach MO, Hawkes DJ (1999) Nonrigid registration using free-form deformations: Application to breast MR images. IEEE Transactions on Medical Imaging 18(8):712–721CrossRefGoogle Scholar
  17. 17.
    Sigal IA, Hardisty MR, Whyne CM (2008) Mesh-morphing algorithms for specimen-specific finite element modeling. Journal of Biomechanics, 1381–1389.Google Scholar
  18. 18.
    Winkler G (2006) Image Analysis, Random Fields and Markov Chain Monte Carlo Methods. Springer, Second editionGoogle Scholar

Copyright information

© Springer-Verlag London 2009

Authors and Affiliations

  • Christof Seiler
    • 1
  • Philippe Büchler
    • 1
  • Lutz-Peter Nolte
    • 1
  • Mauricio Reyes
    • 1
  • Rasmus Paulsen
    • 2
  1. 1.University of Bern, ARTORG CenterBernSwitzerland
  2. 2.Technical University of Denmark, DTU InformaticsLyngbyDenmark

Personalised recommendations