Abstract
We propose a new similarity measure for atlas-to-image matching in the context of atlas-driven intensity-based tissue classification of MR brain images. The new measure directly matches probabilistic tissue class labels to study image intensities, without need for an atlas MR template. Non-rigid warping of the atlas to the study image is achieved by free-form deformation using a viscous fluid regularizer such that mutual information (MI) between atlas class labels and study image intensities is maximized. The new registration measure is compared with the standard approach of maximization of MI between atlas and study images intensities. Our results show that the proposed registration scheme indeed improves segmentation quality, in the sense that the segmentations obtained using the atlas warped with the proposed non-rigid registration scheme better explain the study image data than the segmentations obtained with the atlas warped using standard intensity-based MI.
Chapter PDF
Similar content being viewed by others
Keywords
- Mutual Information
- Class Label
- Gaussian Mixture Model
- Grey Matter Intensity
- Joint Probability Distribution
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.
References
Cocosco, C.A., Kollokian, V., Kwan, R.K.-S., Evans, A.C.: BrainWeb: Online Interface to a 3D MRI Simulated Brain Database. In: Proceedings of 3-rd International Conference on Functional Mapping of the Human Brain, vol. 5(4), part 2/4, p. S425 (1997)
The SPM package is available online at, http://www.fil.ion.ucl.ac.uk/spm/
Maes, F., Collignon, A., Vandermeulen, D., Marchal, G., Suetens, P.: Multimodality image registration by maximization of mutual information. IEEE Trans. Medical Imaging 16(4), 187–198 (1997)
Van Leemput, K., Maes, F., Vandermeulen, D., Suetens, P.: Automated model-based tissue classification of MR images of the brain. IEEE Trans. Medical Imaging 18(10), 897–908 (1999)
D’Agostino, E., Maes, F., Vandermeulen, D., Suetens, P.: A viscous fluid model for multimodal non-rigid image registration using mutual information. Medical Image Analysis 7(4), 565–575 (2003)
D’Agostino, E., Maes, F., Vandermeulen, D., Suetens, P.: An information theoretic approach for non-rigid image registration using voxel class probabilities. In: Ellis, R.E., Peters, T.M. (eds.) MICCAI 2003. LNCS, vol. 2879, pp. 812–820. Springer, Heidelberg (2003)
Kim, J., Fisher III, J.W., Yezzi Jr., A., Cetin, M., Willsky, A.S.: Nonparametric methods for image segmentation using information theory and curve evolution IEEE ICIP 2002. In: IEEE International Conference on Image Processing, Rochester, New York, September 2002, vol. 3, pp. 797–800 (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
D’Agostino, E., Maes, F., Vandermeulen, D., Suetens, P. (2004). Non-rigid Atlas-to-Image Registration by Minimization of Class-Conditional Image Entropy. In: Barillot, C., Haynor, D.R., Hellier, P. (eds) Medical Image Computing and Computer-Assisted Intervention – MICCAI 2004. MICCAI 2004. Lecture Notes in Computer Science, vol 3216. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30135-6_91
Download citation
DOI: https://doi.org/10.1007/978-3-540-30135-6_91
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22976-6
Online ISBN: 978-3-540-30135-6
eBook Packages: Springer Book Archive