Robust Computation of Mutual Information Using Spatially Adaptive Meshes

We present a new method for the fast and robust computation of information theoretic similarity measures for alignment of multi-modality medical images. The proposed method defines a non-uniform, adaptive sampling scheme for estimating the entropies of the images, which is less vulnerable to local maxima as compared to uniform and random sampling. The sampling is defined using an octree partition of the template image, and is preferable over other proposed methods of non-uniform sampling since it respects the underlying data distribution. It also extends naturally to a multi-resolution registration approach, which is commonly employed in the alignment of medical images. The effectiveness of the proposed method is demonstrated using both simulated MR images obtained from the BrainWeb database and clinical CT and SPECT images.

[1]  W. Press,et al.  Numerical Recipes in Fortran: The Art of Scientific Computing.@@@Numerical Recipes in C: The Art of Scientific Computing. , 1994 .

[2]  Donald Meagher,et al.  Geometric modeling using octree encoding , 1982, Comput. Graph. Image Process..

[3]  Henry Fuchs,et al.  On visible surface generation by a priori tree structures , 1980, SIGGRAPH '80.

[4]  Stan Z. Li,et al.  Markov Random Field Modeling in Computer Vision , 1995, Computer Science Workbench.

[5]  Paul A. Viola,et al.  Alignment by Maximization of Mutual Information , 1997, International Journal of Computer Vision.

[6]  Paul W. Fieguth,et al.  An overlapping tree approach to multiscale stochastic modeling and estimation , 1997, IEEE Trans. Image Process..

[7]  Max A. Viergever,et al.  Image registration by maximization of combined mutual information and gradient information , 2000, IEEE Transactions on Medical Imaging.

[8]  P. Pérez,et al.  Markov random fields and images , 1998 .

[9]  Dinggang Shen,et al.  Multi-modal Image Registration by Quantitative-Qualitative Measure of Mutual Information (Q-MI) , 2005, CVBIA.

[10]  A Collignon,et al.  Automated multimodality image registration using information theory , 1995 .

[11]  Colin Studholme,et al.  An overlap invariant entropy measure of 3D medical image alignment , 1999, Pattern Recognit..

[12]  Charles A. Bouman,et al.  A multiscale random field model for Bayesian image segmentation , 1994, IEEE Trans. Image Process..

[13]  Guy Marchal,et al.  Automated Multimodality Medical Images Registration using Information Theory , 1995 .

[14]  F. A. Seiler,et al.  Numerical Recipes in C: The Art of Scientific Computing , 1989 .

[15]  W. Clem Karl,et al.  Efficient multiscale regularization with applications to the computation of optical flow , 1994, IEEE Trans. Image Process..

[16]  Max A. Viergever,et al.  Mutual-information-based registration of medical images: a survey , 2003, IEEE Transactions on Medical Imaging.

[17]  Samson J. Timoner.  Compact representations for fast nonrigid registration of medical images , 2003 .

[18]  Paul A. Viola,et al.  Multi-modal volume registration by maximization of mutual information , 1996, Medical Image Anal..

[19]  Jon Louis Bentley,et al.  Quad trees a data structure for retrieval on composite keys , 1974, Acta Informatica.

[20]  D. Louis Collins,et al.  Design and construction of a realistic digital brain phantom , 1998, IEEE Transactions on Medical Imaging.

[21]  Sang Joon Kim,et al.  A Mathematical Theory of Communication , 2006 .

[22]  William H. Press,et al.  The Art of Scientific Computing Second Edition , 1998 .

[23]  M.R. Sabuncu,et al.  Gradient based nonuniform subsampling for information-theoretic alignment methods , 2004, The 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.