Automatic Estimation of the Number of Segmentation Groups Based on MI
- 2.2k Downloads
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.
KeywordsMutual Information Segmentation Result Magnetic Resonance Data Markov Random Field Model Medical Imaging Segmentation
Unable to display preview. Download preview PDF.
- 1.Bankman, I.: Handbook of Medical Image Processing and Analysis, pp. 71–258 (2008) ISBN 978-0-12-373904-9Google Scholar
- 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.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
- 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
- 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.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.Markov, S.Z.L.: Random Field Modeling in Image Analysis, pp. 19–21. Springer, Heidelberg (2001)Google Scholar
- 11.Brain Web. Montreal Neurological Institute, McGill University (2006), http://www.bic.mni.mcgill.ca/brainweb/