Multimodal Image Registration for Medical Images

In this paper, a technique for registering medical images captured through different modalities with focus on portal image is been discussed. Earlier template matching was used to register satellite images, but it does not serve the purpose as images are from different modalities and same objects are represented with different intensity values. Mutual information based techniques outperform other multimodal techniques for this application because of inherently poor quality acquired image through MV image during patient treatment. This technique will suffer if image is very blurry. The technique is to maximize the mutual information between two images using gradient ascent method.

[1]  Sabyasachi Pattnaik,et al.  Fast Convergence Particle Swarm Optimization for Functions Optimization , 2012 .

[2]  Zhixun Su,et al.  A novel hierarchical medical image registration method based on multiscale and contour line , 2012, 2012 International Conference on Systems and Informatics (ICSAI2012).

[3]  Guy Marchal,et al.  Multimodality image registration by maximization of mutual information , 1997, IEEE Transactions on Medical Imaging.

[4]  Fumihiko Ino,et al.  Efficient Acceleration of Mutual Information Computation for Nonrigid Registration Using CUDA , 2014, IEEE Journal of Biomedical and Health Informatics.

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

[6]  Lisa M. Brown,et al.  A survey of image registration techniques , 1992, CSUR.

[7]  Anil K. Jain.  Fundamentals of Digital Image Processing , 2018, Control of Color Imaging Systems.

[8]  Christos Davatzikos,et al.  A novel 2D-3D registration algorithm for aligning fluoro images with 3D pre-op CT/MR images , 2006, SPIE Medical Imaging.

[9]  C. E. SHANNON,et al.  A mathematical theory of communication , 1948, MOCO.

[10]  Pablo Suau,et al.  Information Theory in Computer Vision and Pattern Recognition , 2009 .

[11]  Athanasios Papoulis,et al.  Probability, Random Variables and Stochastic Processes , 1965 .

[12]  A. Ardeshir Goshtasby,et al.  Volume image registration by template matching , 2001, Image Vis. Comput..

[13]  Somaraju Boda,et al.  Feature-Based Image Registration , 2009 .

[14]  Harsa Amylia Mat Sakim,et al.  MR image monomodal registration based on the nonsubsampled contourlet transform and mutual information , 2010, 2010 International Conference on Computer Applications and Industrial Electronics.

[15]  William M. Wells,et al.  2D-3D vascular registration between digital subtraction angiographic (DSA) and magnetic resonance angiographic (MRA) images , 2004, 2004 2nd IEEE International Symposium on Biomedical Imaging: Nano to Macro (IEEE Cat No. 04EX821).

[16]  Ranjan Bose,et al.  Information theory, coding and cryptography , 2003 .

[17]  Bruno O. Shubert,et al.  Random variables and stochastic processes , 1979 .

[18]  Kawal S. Rhode,et al.  Registration and tracking to integrate X-ray and MR images in an XMR Facility , 2003, IEEE Transactions on Medical Imaging.

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

[20]  Paul A. Viola,et al.  Alignment by Maximization of Mutual Information , 1995, Proceedings of IEEE International Conference on Computer Vision.

[21]  Kawal S. Rhode,et al.  Intensity-based 2-D - 3-D registration of cerebral angiograms , 2003, IEEE Transactions on Medical Imaging.