Intensity Gradient Based Registration and Fusion of Multi-modal Images

Summary

Objectives: A particular problem in image registration arises for multi-modal images taken from different imaging devices and/or modalities. Starting in 1995, mutual information has shown to be a very successful distance measure for multi-modal image registration. Therefore, mutual information is considered to be the state-of-the-art approach to multi-modal image registration. However, mutual information has also a number of well-known drawbacks. Its main disadvantage is that it is known to be highly non-convexand hastypicallymanylocal maxima.

Methods: This observation motivates us to seek a different image similarity measure which is better suited for optimization but as well capable to handle multimodal images.

Results: In this work, we investigate an alternative distance measure which is based on normalized gradients.

Conclusions: As we show, the alternative approach is deterministic, much simpler, easier to interpret, fast and straightforward to implement, faster to compute, and also much more suitable to numerical optimization.

Keywords

Image registration - warping - fusion - distance images - mutual information

• References

• 1 Ascher U, Haber E, Haung H. On effective methods for implicit piecewise smooth surface recovery. SIAM J of Scientific Computing 2006; 28 (01) 339-358.
• 2 Gottesfeld Brown L. A survey of image registration techniques. ACM Computing Surveys 1992; 24 (04) 325-376.
• 3 Cocosco CA, Kollokian V, Kwan RK, Evans AC. Brain-Web MR simulator. Available at http://www.bic.mni.mcgill.ca/brainweb/.
• 4 Collignon A, Vandermeulen A, Suetens P, Marchal G. Multimodality medical image registration based on information theory. Computational Imaging and Vision 1995; 03: 263-274.
• 5 Dennis JE, Schnabel RB. Numerical methods for unconstrained optimization and nonlinear equations.. Philadelphia: SIAM; 1996
• 6 Droske M, Rumpf M. A variational approach to non-rigid morphological registration. SIAM Appl Math 2004; 64 (02) 668-687.
• 7 Fitzpatrick JM, Hill D LG, Maurer CR. Image registration. Handbook of medical imaging. Volume 2: Medical Image Processing and Analysis. 2000. SPIE; 447-513.
• 8 Gallardo LA, Meju MA. Characterization of heterogeneous nearsurface materials by joint 2d inversion of dc resistivity and seismic data. Geophys Res Lett 2003; 30 (13) 1658-1664.
• 9 Golub G, Heath M, Wahba G. Generalized cross-validation as amethod for choosing a good ridge parameter. Technometrics 1979; 21: 215-223.
• 10 Haber E, Oldenburg D. Joint inversion a structural approach. Inverse Problems 1997; 13: 63-67.
• 11 Haber E, Modersitzki J. A multilevel method for image registration. SIAM J of Scientific Computing 2006; 27 (05) 1594-1607.
• 12 Lehmann TM, Meinzer HP, Tolxdorff T. Advances in biomedical image analysis – past, present and future challenges. Methods Inf Med 2004; 43 (04) 308-314.
• 13 Lester H, Arridge SR. A survey of hierarchical non-linear medical image registration. Pattern Recognition 1999; 32: 129-149.
• 14 Modersitzki J. Numerical methods for image registration.. Oxford: 2004
• 15 Park H, Bland PH, Brock KK, Meyer CR. Adaptive registration using local informationmeasures. Medical Image Analysis 2004; 08: 465-473.
• 16 Josien PW, Pluim JPW, Maintz JBA, Viergever MA. Image registration by maximization of combined mutual information and gradient information. IEEE TMI 2000; 19 (08) 809-814.
• 17 Pluim JPW, Maintz JBA, Viergever MA. Interpolation artifacts in mutual information based image registration. CVIV 2000; 77 (02) 211-232.
• 18 Pluim JPW, Maintz JBA, Viergever MA. Mutual-information-based registration of medical images: a survey. IEEE Transactions on Medical Imaging 1999; 22 (09) 986-1004.
• 19 Rudin L, Osher S, Fatemi E. Nonlinear total variation based noise removal algorithms. Proceedings of the eleventh annual international conference of the Center for Nonlinear Studies on Experimental mathematics: computational issues in nonlinear science. 1992: 259-268.
• 20 Silverman R. Density estimation for statistics and data analysis.. Chapman & Hall; 1992
• 21 Trottenberg U, Oosterlee C, Schuller A. Multigrid.. Academic Press; 2001
• 22 Unser M, Thévenaz P. Stochastic sampling for computing the mutual information of two images. Proceedings of the Fifth International Workshop on Sampling Theory and Applications (Samp-TA’03). Strobl, Austria: 2003: 102-109.
• 23 Viola PA. Alignment by maximization of mutual information. Ph.D. thesis.. Massachusetts Institute of Technology; 1995
• 24 Wahba G. Spline models for observational data.. SIAM; Philadelphia: 1990
• 25 Yoo TS. Insight into images: Principles and practice for segmentation, registration, and image analysis.. AK Peters Ltd; 2004
• 26 Zhang J, Morgan FD. Joint seismic and electrical tomography, Proceedings of the EEGS Symposium on Applications of Geophysics to Engineering and Environmental Problems. 1996: 391-396.
• 27 Zitová B, Flusser J. Image registration methods: a survey. Image and Vision Computing 2003; 21 (11) 977-1000.