Medical Image Registration Based on BSP and Quad-Tree Partitioning
This paper presents a study of image simplification techniques as a first stage to define a multiresolution registration framework. We propose here a new approach for image registration based on the partitioning of the source images in binary-space (BSP) and quad-tree structures. These partitioned images have been obtained with a maximum mutual information gain algorithm. Multimodal registration experiments with downsampled, BSP and quadtree partitioned images show an outstanding accuracy and robustness by using BSP images, since the grid effects are drastically reduced. The obtained results indicate that BSP partitioning can provide a suitable framework for multiresolution registration.
KeywordsMutual Information Image Registration Source Image Normalize Mutual Information Marginal Probability Distribution
Unable to display preview. Download preview PDF.
- 1.Cover, T.M., Thomas, J.A.: Elements of Information Theory. Wiley Series in Telecommunications (1991)Google Scholar
- 3.National Institutes of Health. Retrospective Image Registration Evaluation. Vanderbilt University, Nashville, TN, USA, Project Number 8R01EB002124-03, Principal Investigator J. Michael Fitzpatrick (2003)Google Scholar
- 6.Studholme, C.: Measures of 3D Medical Image Alignment. PhD thesis, University of London, London, UK (August 1997)Google Scholar
- 8.Unser, M., Thévenaz, P.: Stochastic sampling for computing the mutual information of two images. In: Proceedings of the 5th International Workshop on Sampling Theory and Applications (SampTA 2003), Strobl, Austria, pp. 102–109 (May 2003)Google Scholar
- 9.Viola, P.A.: Alignment by Maximization of Mutual Information. PhD thesis, Massachusetts Institute of Technology, Massachusetts, MA, USA (1995)Google Scholar