Study on Human Brain Registration Process Using Mutual Information and Evolutionary Algorithms
The registration of brain images is required to facilitate the study of brain mapping, treatment planning, and image-guided therapies of nervous system. In the present work a similarity measure has been implemented for affine multimodality (MR and CT) image registration of sections of the human brain. In addition, a similarity measure is built on both intensity and gradient-based images. In the present work, the region of interest (ROI), the ventricular region, is segmented using the fuzzy c-means clustering technique. The deformation or change of shape of the ventricular region captures the process of degeneracy and other abnormality in tissue regions of the human brain. The similarity metric should be maximal when two images are perfectly aligned. The genetic algorithm-based search strategy has been utilized to optimize the registration process.
KeywordsGenetic Algorithm Mutual Information Cluster Center Reference Image Image Registration
The authors would like to thank Dr. S. K. Sharma, Director, EKO Imaging and X-Ray Institute, Kolkata and All India Institute of Medical Sciences, New Delhi.
- 1.Bhattacharya, M., Dutta Majumder, D.: Multi resolution medical image registration using mutual information and shape theory. In: Proceedings of Fourth International Conference on advances in Pattern Recognition and Digital, Techniques, ICAPRDT ’99 (IAPR), pp. 175–178 (1999)Google Scholar
- 3.Butz, T., Thiran, J.-P.: Affine registration with feature space mutual information. In: Niessen, W.J., Viergever, M.A. (eds.) Medical Image Computing and Computer-Assisted Intervention. Lecture Notes in Computer Science, vol. 2208, pp. 549–556. Springer, Berlin (2001)Google Scholar
- 6.Das, A., Bhattacharya, M.: Affine based registration of CT and MR modality images of human brain using multiresolution approaches: comparative study on genetic algorithm and particle-swarm optimization. Neural Comput. Appl. (Springer London) 20(2), 223–237 (2011)Google Scholar
- 7.Dasgupta, D., McGregor, D.R.: Digital image registration using structured genetic algorithms. In: Proceeding of the SPIE, vol. 1766, pp. 226–234 (1992)Google Scholar
- 9.Hill, D.L.G., Hawkes, D.J., Hussain, Z., Green, S.E.M., Ruff, C.F., Robinson, G.P.: Accurate combination of CT and MR data of the head: validation and applications in surgical and therapy planning. Comput. Med. Imaging Graph. 17(4/5), 357–363 (1993)Google Scholar
- 10.Johansson, M.: Image registration with simulated annealing and genetic algorithms. Master’s Thesis in Computer Science at the School of Computer Science and Engineering, Royal Institute of Technology (2006)Google Scholar
- 11.Junck, L., Moen, J.G., Hutchins, G.D., Brown, M.B., Kuhl, D.E.: Correlation methods for the centering, rotation, and alignment of functional brain images. J. Nucl. Med. 31, 1220–1276 (1990)Google Scholar
- 15.Roche, A., Malandain, G., Pennec, X., Ayache, N.: The correlation ratio as a new similarity measure for multimodal image registration. In: First International Conference on Medical Robotics, Imaging And Computer Assisted Surgery (MICCAI’98), ser. Lecture Notes in Computer Science, vol. 1496, pp. 1115–1124. Springer, Cambridge, MA (1998)Google Scholar
- 17.Zhang, H., Zhou, X., Sun, J., Zhang, J.: A novel medical image registration method based on mutual information and genetic algorithm. In: IEEE Proceedings of the Computer Graphics, Imaging and Vision: CGIV, pp. 221–226 (2005)Google Scholar