Multi-Modal Medical Image Registration of by Combining Improved Mean Shift and RPM

Abstract:

Landmark correspondence plays a decisive role in the landmark-based multi-modality image registration. We combine RPM (Robust Point Matching) and improved Mean Shift to estimate the correspondence of landmarks in images. We improve the target mode and bandwidth used in Mean Shift, and we also perform RPM to estimate the initial landmark correspondence. Next, we use improved Mean Shift to adjust corresponding relations between points. Our method is benefit to make corresponding relations between points more accurate and impels the convergence process of RPM to be related to the image content. Experimental results show that our method can achieve accurate registration of the multi-modal images.

• Periodical: Applied Mechanics and Materials (Volumes 239-240)
• Pages: 1472-1475
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.239-240.1472
• Online since: December 2012
• Authors: Dan Ai, Jing Li Shi, Jun Jun Cao, Hong Yan Zhong
• Keywords: Image Registration, Mean-Shift, Multi-Modality, Robust Point Matching

References

[1] Ali Gholipour and Nasser Kehtanavazk. Brain Functional Localization: A survey of image registration techniques, IEEE transactions on medical imaging, PA (2007), vol.26, p.4.

[2] B.Likar,F.Pernus, J. A hierarchical approach to elastic registration based on mutual information. Image and vision computing, 19:33-44 (2001).

DOI: 10.1016/s0262-8856(00)00053-6

[3] J.P. Pluim, J.B.A. Maintz, M.A. Viegever, Image registration by maximization of combined mutual information, IEEE, Trans.on Medical Imaging, August 2000,vol.19(8),pp.809-814

DOI: 10.1109/42.876307

[4] H. Chui and A. Rangarajan, "A New Point Matching Algorithm for Non-Rigid Registration," Computer Vision and Image nderstanding, vol. 89, nos. 2-3, pp.114-141(2003).

DOI: 10.1016/s1077-3142(03)00009-2

[5] Fukunaga,K.,& Hosterler,L.D, The estimation of the gradient of a density function, with application in pattern recognition, J. IEEE Transactions on Information Theory,21,32-40(1975).

DOI: 10.1109/tit.1975.1055330

[6] D. Comaniciu, V. Ramesh, P. Meer. Kernel-based object tracking, IEEE Trans. Pattern Anal. Mach. Intell. (PAMI) 25 (5) 564–577(2003).

DOI: 10.1109/tpami.2003.1195991

[7] Yang, X., Pei, J.H.: Rapid and Robust Medical Image Elastic Registration using Mean Shift. In: Chinese Optics Letters. vol.6(12), p.950(2008)

DOI: 10.3788/col20080612.0950

[8] Wei Sun, Xuan Yang, Nonrigid image registration based on control points matching and shifting. Optical Engineering 50(2)(2011).

DOI: 10.1117/1.3542043