Automatic Estimation of the Number of Segmentation Groups Based on MI

  • Ziming Zeng
  • Wenhui Wang
  • Longzhi Yang
  • Reyer Zwiggelaar
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6669)


Clustering is important in medical imaging segmentation. The number of segmentation groups is often needed as an initial condition, but is often unknown. We propose a method to estimate the number of segmentation groups based on mutual information, anisotropic diffusion model and class-adaptive Gauss-Markov random fields. Initially, anisotropic diffusion is used to decrease the image noise. Subsequently, the class-adaptive Gauss-Markov modeling and mutual information are used to determine the number of segmentation groups. This general formulation enables the method to easily adapt to various kinds of medical images and the associated acquisition artifacts. Experiments on simulated, and multi-model data demonstrate the advantages of the method over the current state-of-the-art approaches.


Mutual Information Segmentation Result Magnetic Resonance Data Markov Random Field Model Medical Imaging Segmentation 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Bankman, I.: Handbook of Medical Image Processing and Analysis, pp. 71–258 (2008) ISBN 978-0-12-373904-9Google Scholar
  2. 2.
    Akaike, H.: A new look at the statistical model identification. IEEE Transactions on Automatic Control 19(6), 716–723 (1974)MathSciNetCrossRefzbMATHGoogle Scholar
  3. 3.
    Lv, Q.W., Chen, W.F.: Image segmentation based on mutual information. Chinese Journal of Computers 29(2), 296–301 (2006)Google Scholar
  4. 4.
    Wang, W.H., Feng, Q.J., Chen, W.F.: Segmentation of brain MR images based on the measurement of difference of mutual information and Gauss-Markov random field model. Journal of Computer Research and Development 46(3), 521–527 (2009)Google Scholar
  5. 5.
    Maes, F., Collignon, A.: Multimodality image registration by maximization of mutual information. IEEE Transactions on Medical Imaging 16(2), 187–198 (1997)CrossRefGoogle Scholar
  6. 6.
    Kim, J., Fisher, J.W., Cetin, M., Yezzi, A., Willsky, A.S.: Incorporating complex statistical information in active contour-based image segmentation. In: International Conference on Image Processing, pp. 655–658 (2003)Google Scholar
  7. 7.
    Perona, P., Malik, J.: Scale-space and edge detection using anisotropic diffusion. IEEE Transactions on Pattern Analysis and Machine Intelligence 12(7), 529–539 (1990)CrossRefGoogle Scholar
  8. 8.
    Tong, C., Wang, S.T., Man, L.H.: Improved image denoising method based on PDE. Journal of Computer Engineering and Applications 46(15), 176–179 (2010)Google Scholar
  9. 9.
    Wang, W.H., Feng, Q.J., Liu, L., Chen, W.F.: Segmentation of brain MR images through class-adaptive Gauss-Markov random field model and the EM algorithm. Journal of Image and Graphics 13(3), 488–493 (2008)Google Scholar
  10. 10.
    Markov, S.Z.L.: Random Field Modeling in Image Analysis, pp. 19–21. Springer, Heidelberg (2001)Google Scholar
  11. 11.
    Brain Web. Montreal Neurological Institute, McGill University (2006),
  12. 12.
    Zhuang, A.H., Valentino, D.J., Toga, A.W.: Skull-stripping magnetic resonance brain images using a model-based level set. NeuroImage 32(1), 79–92 (2006)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Ziming Zeng
    • 1
    • 2
  • Wenhui Wang
    • 3
    • 4
  • Longzhi Yang
    • 1
  • Reyer Zwiggelaar
    • 1
  1. 1.Department of Computer ScienceAberystwyth UniversityUK
  2. 2.Faculty of Information and Control EngineeringShenyang Jianzhu UniversityLiaoningChina
  3. 3.Network Information Center of the Sixth Affiliated Hospital of Sun Yat-sen UniversityGuangzhouChina
  4. 4.Key Laboratory of Medical Image ProcessingSouthern Medical UniversityGuangzhouChina

Personalised recommendations