×

Intensity-based robust similarity for multimodal image registration. (English) Zbl 1086.94003

Summary: This paper proposes a new intensity-based similarity metric that can be used for the registration of multimodal images. It combines the robust estimation with both the forward and inverse transformation to reduce the negative effects of outliers in the images. For this purpose, we firstly employ the multiresolution technique to downsample the original images, then resort to the simulated annealing method to initialize the transformation parameters at the coarsest resolution. Finally the Powell method is utilized to obtain the optimal transformation parameters at each resolution. In our experiments, the new method is compared to other popular similarity measures, on the synthetic data as well as the real data, and the experimental results are encouraging.

MSC:

94A08 Image processing (compression, reconstruction, etc.) in information and communication theory

Software:

ASA
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Fitzpatrick J., IEEE Transactions on Medical Imaging 17 pp 694– (1998) · doi:10.1109/42.736021
[2] Frantz, S., Rohr, K., Stiehl, H. S., Kim, S.I. and Weese, J. Validating point-based MR/CT registration based on semi-automatic landmark extraction. Proceedings of CARS’99. pp.233–237. Asterdam: Elsevier Science.
[3] Lemoine, D., Liegeard, D., Lussot, D. and Barillot, C. Proceedings of SP. Vol. 2164, pp.46–56.
[4] Davatzikos C., IEEE Transactions on Medical Imaging 15 pp 112– (1996) · doi:10.1109/42.481446
[5] Hsu L., IEEE Engineering in Medicine and Biology Magazine 18 pp 40– (1999) · doi:10.1109/51.805143
[6] Besl P. J., IEEE Transactions on Pattern Analysis and Machine Intelligence 14 pp 239– (1992) · Zbl 05110721 · doi:10.1109/34.121791
[7] Banerjee P. K., Physics in Medicine and Biology 39 pp 1969– (1994) · doi:10.1088/0031-9155/39/11/011
[8] Hajnal J. V., Journal of Computer Assisted Tomography 19 pp 667– (1995)
[9] Woods R. P., Journal of Computer Assisted Tomography 17 pp 536– (1993) · doi:10.1097/00004728-199307000-00004
[10] Maes F., IEEE Transactions on Medical Imaging 16 pp 187– (1997) · doi:10.1109/42.563664
[11] Thevenaz P., IEEE Transactions on Image Processing 9 pp 2083– (2000) · Zbl 0993.94534 · doi:10.1109/83.887976
[12] Ding E., Medical Imaging 2000 pp 1235– (2000)
[13] Studholme C., Medical Image Analysis 1 pp 163– (1996) · doi:10.1016/S1361-8415(96)80011-9
[14] Shekhar R., IEEE Transactions on Medical Imaging 21 pp 9– (2002) · doi:10.1109/42.981230
[15] He R., Computerized Medical Imaging and Graphics 26 pp 277– (2002) · Zbl 05327771 · doi:10.1016/S0895-6111(02)00019-8
[16] Hellier P., IEEE Transactions on Medical Imaging 20 pp 388– (2001) · doi:10.1109/42.925292
[17] Meer P., International Journal of Computer Vision 6 pp 59– (1990) · doi:10.1007/BF00127126
[18] Nikou C., NeuroImage 8 pp 30– (1998) · doi:10.1006/nimg.1998.0335
[19] Black M. J., International Journal of Computer Vision 19 pp 57– (1996) · Zbl 05475543 · doi:10.1007/BF00131148
[20] Huber P. J., Robust Statistics (1981) · Zbl 0536.62025 · doi:10.1002/0471725250
[21] Press W. H., Numerical Recipes in C (1992) · Zbl 0778.65003
[22] Ingber, L. 1995. ”Adaptive simulated annealing (ASA)”. McLean, VA: Lester Ingber Research. Technical Report · Zbl 0860.93035
[23] Cocosco C. A., NeuroImage 5 pp S425– (1997)
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.