Advertisement

A Markov random field model for bony tissue classification

  • J. M. Pardo
  • D. Cabello
  • J. Heras
Poster Session D: Biomedical Applications, Detection, Control & Surveillance, Inspection, Optical Character Recognition
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1311)

Abstract

3D biomedical images constitute an indispensable source of information for the clinical diagnostic. In the case of bone structure images, a system that automatically interprets and presents a 3D shape reconstruction of the bone would be of great aid in areas such as bone remodeling, fracture prediction and prothesis design. In these tasks, external geometry needs to be precisely defined and lesions and pathologies identified. The object recognition task can rarely be carried out without knowledge on the domain. This knowledge may be introduced as a set of constraints over features and relationships between the regions obtained by means of a presegmentation. A formal scheme for the integration of this set of constraints and the solution of the interpretation problem is provided by the Markov Random Field (MRF) model. In this work we present a MRF model for identification of lesions and pathologies in the proximal tibia.

Keywords

Proximal Tibia Markov Random Field Gibbs Distribution Object Recognition Task Markov Random Field Model 
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.
    M. Sonka, W. Park, and E. A. Hoffman. Rule-based detection of intrathoracic airway trees. IEEE Transactions on Medical Imaging, 15(3):314–326, June 1996.CrossRefGoogle Scholar
  2. 2.
    J. W. Modestino and J. Zhang. A Markov random field model-based approach to image interpretation. IEEE Trans. Patt. Anal. Machine. Intell., 14(6):606–615, 1992.CrossRefGoogle Scholar
  3. 3.
    I. Y. Kim and H. S. Yang. An interpretation scheme for image segmentation and labeling based on Markov random field model. IEEE Trans. Patt. Anal. Machine. Intell., 18(1):69–73, 1996.CrossRefGoogle Scholar
  4. 4.
    S. Z. Li. Markov Random Field Modeling in Computer Vision. Springer-Verlag, Tokio, 1995.Google Scholar
  5. 5.
    J. M Pardo, D. Cabello, M. J. Carreira, M. G. Penedo, and J. Heras. Knowledge-based CT image analysis: automatic 3d shape reconstruction of bones. In Proc. of the Second Asian Conference on Computer Vision, volume 1, pages 504–508, 1995.Google Scholar
  6. 6.
    S. Geman and D. Geman. Stochastic relaxation, Gibbs distribution, and Bayesian restoration of images. IEEE Trans. Patt. Anal. Machine. Intell., 6(6):721–741, 1984.Google Scholar
  7. 7.
    J. M Pardo, D. Cabello, M.J. Carreira, and J. Heras. Integrating region and edge information in CT image segmentation. In A. Sanfeliu, J.J. Villanueva, and J. Vitria, editors, Patern Recognition and Image Analysis, volume 1, pages 7–12. 1997.Google Scholar
  8. 8.
    D. Cabello, M. G. Penedo, S. Barro, J. M. Pardo, and J. Heras. CT image segmentation by self-organazing learning. In J. Mira, J. Cabestany, and A. Prieto, editors, New trends in neural computation, volume 686, pages 651–656. Spring-Verlag, 1993.Google Scholar
  9. 9.
    S. Kirkpatrick, C. D. Gelatt, and M. P. Vecchi. Optimization by simulated annealing. Science, 220:671–680, 1983.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • J. M. Pardo
    • 1
  • D. Cabello
    • 1
  • J. Heras
    • 2
  1. 1.Depto. Electrónica e ComputaciónFacultade de FísicaSpain
  2. 2.Servicio de Ciruxía Ortopédica. Hospital Xeral de GaliciaUniversidade de Santiago de CompostelaSpain

Personalised recommendations