A Framework for Unsupervised Segmentation of Multi-modal Medical Images

  • Ayman El-Baz
  • Aly Farag
  • Asem Ali
  • Georgy Gimel’farb
  • Manuel Casanova
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4241)

Abstract

We propose new techniques for unsupervised segmentation of multi-modal grayscale images such that each region-of-interest relates to a single dominant mode of the empirical marginal probability distribution of gray levels. We follow most conventional approaches such that initial images and desired maps of regions are described by a joint Markov–Gibbs random field (MGRF) model of independent image signals and interdependent region labels. But our focus is on more accurate model identification. To better specify region borders, each empirical distribution of image signals is precisely approximated by a linear combination of Gaussians (LCG) with positive and negative components. Initial segmentation based on the LCG-models is then iteratively refined by using the MGRF with analytically estimated potentials. The convergence of the overall segmentation algorithm at each stage is discussed. Experiments with medical images show that the proposed segmentation is more accurate than other known alternatives.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Kaufhold, J., Hoogs, A.: Learning to segment images using region-based perceptual features. In: Proc. IEEE Int. Conf. on Computer Vision and Pattern Recognition (CVPR 2004), vol. 1, pp. 954–961 (2004)Google Scholar
  2. 2.
    Ren, X., Malik, J.: Learning a classification model for segmentation. In: Proc. 9th IEEE Int. Conf. on Computer Vision (ICCV 2003), Nice, France, October 14–17, vol. 1, pp. 10–17. IEEE CS Press, Los Alamitos (2003)CrossRefGoogle Scholar
  3. 3.
    Tu, Z., Chen, X., Yuille, A.L., Zhu, S.C.: Image parsing: Unifying segmentation, detection, and recognition. In: Proc. 9th IEEE Int. Conf. on Computer Vision (ICCV 2003), Nice, France, October 14–17, vol. 1, pp. 18–25. IEEE CS Press, Los Alamitos (2003)Google Scholar
  4. 4.
    Yu, S.X.: Segmentation using multiscale cues. In: Proc IEEE Int. Conf. on Computer Vision and Pattern Recognition (CVPR 2004), vol. 1, pp. 247–254 (2004)Google Scholar
  5. 5.
    Singh, M., Ahuja, N.: Regression based bandwidth selection for segmentation using Parzen windows. In: Proc. 9th IEEE Int. Conf. on Computer Vision (ICCV 2003), Nice, France, October 14–17, 2003, vol. 1, pp. 2–9. IEEE CS Press, Los Alamitos (2003)CrossRefGoogle Scholar
  6. 6.
    Grzeszczuk, R.P., Levin, D.N.: Brownian strings: Segmenting images with stochastically deformable contours. IEEE Trans. Pattern Anal. Machine Intell. 19, 1100–1114 (1997)CrossRefGoogle Scholar
  7. 7.
    Huang, X., Metaxas, D., Chen, T.: MetaMorphs: Deformable shape and texture models. In: Proc. IEEE Int. Conf. on Computer Vision and Pattern Recognition (CVPR 2004), vol. 1, pp. 496–503 (2004)Google Scholar
  8. 8.
    Xu, C., Prince, J.L.: Snakes, shapes, and gradient vector flow. IEEE Trans. Pattern Anal. Machine Intell. 7(3), 359–369 (1998)MATHMathSciNetGoogle Scholar
  9. 9.
    Yuen, P.C., Feng, G.C., Zhou, J.P.: A contour detection method: Initialization and contour model. Pattern Recognition Letters 20, 141–148 (1999)MATHCrossRefGoogle Scholar
  10. 10.
    Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification. Wiley, New York (2001)MATHGoogle Scholar
  11. 11.
    Schlesinger, M.I., Hlavac, V.: Ten Lectures on Statistical and Structural Pattern Recognition. Kluwer, Dordrecht (2002)MATHGoogle Scholar
  12. 12.
    Bouman, C.A., Shapiro, M.: A multiscale random field model for Bayesian image segmentation. IEEE Trans. Image Processing 3(2), 162–177 (1994)CrossRefGoogle Scholar
  13. 13.
    Farag, A.A., El-Baz, A., Gimelfarb, G.: Density Estimation Using Modified Expectation Maximization for a linear combination of Gaussians. In: Proc. of IEEE International Conference on Image Processing (ICIP 2004), Singapore, October 24–27, vol. I, pp. 194–197 (2004)Google Scholar
  14. 14.
    Dubes, R.C., Jain, A.K.: Random field models in image analysis. J. Applied Statistics 16(2), 131–164 (1989)CrossRefGoogle Scholar
  15. 15.
    Picard, R.W., Elfadel, I.M.: Structure of aura and cooccurrence matrices for the Gibbs texture model. J. Math. Imaging and Vision 2(1), 5–25 (1992)CrossRefGoogle Scholar
  16. 16.
    Dryden, L., Scarr, M.R., Taylor, C.C.: Bayesian texture segmentation of weed and crop images using reversible jump Markov chain Monte Carlo methods. J. Royal Statistical Society 52(1), 31–50 (2003)MATHCrossRefMathSciNetGoogle Scholar
  17. 17.
    Lamperti, J.W.: Probability. J. Wiley & Sons, New York (1996)MATHGoogle Scholar
  18. 18.
    Hu, S., Hoffman, E.A.: Automatic lung segmentation for accurate quantization of volumetric X-Ray CT images. IEEE Trans. Medical Imaging 20(6), 490–498 (2001)CrossRefGoogle Scholar
  19. 19.
    Bouman, C., Liu, B.: Multiple resolution segmentation of textured images. IEEE Trans. Pattern Analysis Machine Intell. 13(2), 99–113 (1991)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Ayman El-Baz
    • 1
  • Aly Farag
    • 1
  • Asem Ali
    • 1
  • Georgy Gimel’farb
    • 2
  • Manuel Casanova
    • 3
  1. 1.Computer Vision and Image Processing LaboratoryUniversity of LouisvilleLouisvilleUSA
  2. 2.Department of Computer ScienceUniversity of AucklandAucklandNew Zealand
  3. 3.Department of PsychiatryUniversity of LouisvilleUSA

Personalised recommendations