Advertisement

Segmentation of Magnetic Resonance images using mean field annealing

  • W Snyder
  • A Logenthiran
  • P Santago
  • K Link
  • G Bilbro
  • S Rajala
4. Segmentation: Specific Applications
Part of the Lecture Notes in Computer Science book series (LNCS, volume 511)

Abstract

The problem of segmentation of Magnetic Resonance images into regions of uniform tissue density is posed as an optimization problem. A new objective function is defined and the resulting minimization problem is solved using Mean Field Annealing, a new technique which usually finds global minima in non-convex optimization problems, and performs particularly well on images. Noise sensitivity is evaluated by tests on synthetic images, and the technique is then applied to clinical images of a brain and a knee. The technique shows considerable promise as a method of quantitative change monitoring.

Key words

Simulated annealing restoration reconstruction optimization 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Baker David C and Aggarwal JK (1988). Geometry guided segmentation of outdoor scenes. SPIE Applications of Artificial Intelligence VI:576–583.Google Scholar
  2. Besag J (1974). Spatial interaction and the statistical analysis of lattice systems. J Royal Stat. Soc., Series B, 36:192–326.Google Scholar
  3. Bilbro G, Mann R, Miller T, Snyder W, Van den Bout D and White M (1989). Optimization by mean field annealing. In: Advances in Neural Information Processing Systems. Morgan-Kauffman, San Mateo.Google Scholar
  4. Bilbro G and Snyder W (1989). Range image restoration using mean field annealing. In: Advances in Neural Network Information Processing Systems. Morgan-Kauffman, San Mateo.Google Scholar
  5. Bilbro G and Snyder W. Mean field annealing, an application to image noise removal. Journal of Neural Network Computing.Google Scholar
  6. Bilbro G and Snyder W. Mean field from relative entropy. Journal of the Optical Society of America A.Google Scholar
  7. Chang Hsuan and Fitzpatrick Michael J (1990). Geometrical image transformation to compensate for MRI distortions. SPIE Vol. 1233 Medical Imaging IV, pp 116–127, February.Google Scholar
  8. Derin H and Elliot H (1987).Modeling and segmentation of noisy and textured images using Gibbs random fields, IEEE Trans PAMI, vol. PAMI 9, pp39–55.Google Scholar
  9. Ehricke HH (1990). Problems and approaches for tissue segmentation in 3D-MR imaging. Proceedings of the SPIE Vol. 1233 Medical Imaging IV: Image Processing, pp 128–137, February.Google Scholar
  10. Geman S and Geman D (1984). Stochastic relaxation, Gibbs distributions, and Bayesian restoration of images, IEEE PAMI, vol 6, no 6.Google Scholar
  11. Hansen FR and Elliott H (1982). Image segmentation using simple Markov field models. Computer Graphics and Image Processing, 20:101–132.Google Scholar
  12. Haralick Rand Shapiro G (1985). Image segmentation techniques. Computer Vision, Graphics, and Image Processing 29:100–132.Google Scholar
  13. Hiriyannaiah H (1990). Signal reconstruction using mean field annealing. PhD Thesis, North Carolina State University, Raleigh.Google Scholar
  14. Hiriyannaiah H, Bilbro GL, Snyder WE and Mann RC (1989). Restoration of piecewise constant images via mean field annealing. Journal of the Optical Society of America A, December:1901–1912.Google Scholar
  15. Kak AC and Slaney M (1988). Principles of computerized tomographic imaging. IEEE Press, New York.Google Scholar
  16. Kapouleas I and Kulikowski C (1988). A model-based system for interpretation of MR human brain scans. Proceedings of the SPIE, Volume 914, Medical Imaging II, Feb.Google Scholar
  17. Kashyap RL and Chellappa R (1983). Estimation and choice of neighbors in spatial-interaction model of images. IEEE Trans. Information Theory, IT-29, pp. 60–72, January.Google Scholar
  18. Lee Rae and Leahy Richard (1990). Multi-spectral tissue classification of MR images using sensor fusion approaches. Proceedings of the SPIE Vol. 1233 Medical Imaging IV: Image Processing,pp 149–157, February.Google Scholar
  19. Morris PG (1986). Nuclear magnetic resonance imaging in medicine and biology. In:, Clarendon Press, Oxford.Google Scholar
  20. Nelson Thomas R (1990). Propagation characteristics of a fractal network: applications to the His-Purkinje conduction system. Proceedings of the SPIE, Newport Beach, California, 1233 Medical Imaging IV: Image Processing, pp 23–32, February.Google Scholar
  21. Shemlon Stephen and Dunn Stanley M (1990). Rule-based interpretation with models of expected structure. In SPIE Vol. 1233 Medical Imaging IV, February, pp 33–44.Google Scholar
  22. van Laarhoven JM and Aarts EHL (1988). Simulated annealing: theory and applications. D. Reidel, Norwell, Mass.Google Scholar
  23. Vannier M et al (1989). Multispectral analysis of magnetic resonance images. Radiology, 221–224.Google Scholar
  24. Wolberg G and Pavlidis T (1985). Restoration of binary images using stochastic relaxation with annealing. Pattern Recognition Letters, 3, 6:375–388.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1991

Authors and Affiliations

  • W Snyder
    • 1
  • A Logenthiran
    • 2
  • P Santago
    • 1
  • K Link
    • 1
  • G Bilbro
    • 3
  • S Rajala
    • 3
  1. 1.Bowman Gray School of MedicineWinston-Salem
  2. 2.AT&T Bell Laboratories, Medical Diagnostic SystemsWinston-Salem
  3. 3.Center for Communications and Signal ProcessingNorth Carolina State UniversityUSA

Personalised recommendations