Medical Image Segmentation Based on Mutual Information Maximization
In this paper we propose a two-step mutual information-based algorithm for medical image segmentation. In the first step, the image is structured into homogeneous regions, by maximizing the mutual information gain of the channel going from the histogram bins to the regions of the partitioned image. In the second step, the intensity bins of the histogram are clustered by minimizing the mutual information loss of the reversed channel. Thus, the compression of the channel variables is guided by the preservation of the information on the other. An important application of this algorithm is to preprocess the images for multimodal image registration. In particular, for a low number of histogram bins, an outstanding robustness in the registration process is obtained by using as input the previously segmented images.
Unable to display preview. Download preview PDF.
- 2.Butz, T., Cuisenaire, O., Thiran, J.-P.: Multi-modal medical image registration: from information theory to optimization objective. In: Proceeding of 14th International Conference on Digital Signal Processing (DSP 2002) (July 2002)Google Scholar
- 6.Slonim, N., Tishby, N.: Agglomerative information bottleneck. In: Proceedings of NIPS-12 (Neural Information Processing Systems), pp. 617–623. MIT Press, Cambridge (2000)Google Scholar
- 7.Studholme, C.: Measures of 3D Medical Image Alignment. PhD thesis, University of London, London, UK (August 1997) Google Scholar
- 8.Čapek, M., Mrož, L., Wegenkittl, R.: Robust and fast medical registration of 3D-multi-modality data sets. In: Proceedings of the International Federation for Medical and Biological Engineering, June 2001, vol. 1, pp. 515–518 (2001)Google Scholar