Abstract
Image registration is the process of aligning sets of similar, but different, intensity image functions to track changes between the images. In medical image problems involving lung images, variational registration models are a very powerful tool which can aid in effective treatment of various lung conditions and diseases. However, a common drawback of many variational models, such as the diffusion model and even optic flow models, is the lack of control of folding in the deformations leading to physically inaccurate transformations. For this reason, such models are generally not suitable for real life lung imaging problems where folding cannot occur.
There are two approaches offering reliable solutions (though not necessarily accurate). The first approach is a parametric model such as the affine registration model, still widely used in many applications, but is unable to track local changes or yield accurate results. The second approach is to impose an extra constraint on the transformation of registration at the cost of increased non-linearity.
An alternative to the second approach, achieving diffeomorphic transforms without adding any constraints, is an inverse consistent model such as by Christensen and Johnson (2001) from computing explicitly both the forward and inverse transforms. However, one must deal with the strong non-linearity in the formulation.
In this paper we first propose a simplified inverse consistent model to avoid the inclusion of strong non-linearities and then a fast non-linear multigrid (NMG) technique to overcome the extra computational work required by the inverse consistent model. Experiments, performed on real medical CT images, show that our proposed inverse consistent model is robust to both parameter choice and non-folding in the transformations when compared with diffusion type models.
References
[1] G. Auzias, O. Colliot, J. A. Glaunès, M. Perrot, J. F. Mangin, A. Trouvé and S. Baillet, Diffeomorphic brain registration under exhaustive sulcal constraints, IEEE Trans. Med. Imaging 30 (2011), no. 6, 1214–1227. 10.1109/TMI.2011.2108665Search in Google Scholar
[2] R. Bajscy and S. Kovac̆ic̆, Multiresolution elastic matching, Comp. Vision Graph. 46 (1989), no. 1, 1–21. 10.1016/S0734-189X(89)80014-3Search in Google Scholar
[3] M. Bazargani, A. Anjos, F. G. Lobo, A. Mollahosseini and H. R. Shahbazkia, Affine image registration transformation estimation using a real coded genetic algorithm with SBX, preprint (2012), https://arxiv.org/abs/1204.2139. 10.1145/2330784.2330990Search in Google Scholar
[4] A. Brandt, Multi-level adaptive solutions to boundary-value problems, Math. Comp. 31 (1977), no. 138, 333–390. 10.1090/S0025-5718-1977-0431719-XSearch in Google Scholar
[5] C. Broit, Optimal registration of deformed images, PhD thesis, University of Pennsylvania, 1981. Search in Google Scholar
[6] T. Brox, C. Bregler and J. Malik, Large displacement optical flow, Computer Vision and Pattern Recognition – CVPR 2009, IEEE Press, Piscataway (2009), 41–48. 10.1109/CVPR.2009.5206697Search in Google Scholar
[7] T. Brox, A. Bruhn, N. Papenberg and J. Weickert, High accuracy optical flow estimation based on a theory for warping, Computer Vision – ECCV 2004, Lecture Notes in Comput. Sci. 3024, Springer, Berlin (2004), 25–36. 10.1007/978-3-540-24673-2_3Search in Google Scholar
[8] T. Brox and J. Malik, Large displacement optical flow: Descriptor matching in variational motion estimation, IEEE Trans. Pattern Anal. Mach. Intelligence 33 (2011), 500–513. 10.1109/TPAMI.2010.143Search in Google Scholar PubMed
[9] A. Bruhn, J. Weickert, C. Feddern, T. Kohlberger and C. Schnörr, Real-time optic flow computation with variational methods, Computer Analysis of Images and Patterns, Lecture Notes in Comput. Sci. 2756, Springer, Berlin (2003), 222–229. 10.1007/978-3-540-45179-2_28Search in Google Scholar
[10] A. Bruhn, J. Weickert, C. Feddern, T. Kohlberger and C. Schnörr, Variational optical flow computation in real time, IEEE Trans. Image Process. 14 (2005), no. 5, 608–615. 10.1109/TIP.2005.846018Search in Google Scholar PubMed
[11] M. Burger, J. Modersitzki and L. Ruthotto, A hyperelastic regularization energy for image registration, SIAM J. Sci. Comput. 35 (2013), no. 1, B132–B148. 10.1137/110835955Search in Google Scholar
[12] K. Cao, G. E. Christensen, K. Ding, K. Du, M. L. Raghavan, R. E. Amelon, K. M. Baker, E. A. Hoffman and J. M. Reinhardt, Tracking regional tissue volume and function change in lung using image registration, Int. J. Biomed. Imaging 2012 (2012), Article ID 956248. 10.1155/2012/956248Search in Google Scholar PubMed PubMed Central
[13] K. Chen, Matrix Preconditioning Techniques and Applications, Cambridge Monogr. Appl. Comput. Math. 19, Cambridge University Press, Cambridge, 2005. 10.1017/CBO9780511543258Search in Google Scholar
[14] Y. Chen and X. Ye, Inverse consistent deformable image registration, The legacy of Alladi Ramakrishnan in the Mathematical Sciences, Springer, New York (2010), 419–440. 10.1007/978-1-4419-6263-8_26Search in Google Scholar
[15] G. E. Christensen and H. J. Johnson, Consistent image registration, IEEE Trans. Med. Imaging 20 (2001), no. 7, 568–582. 10.1109/42.932742Search in Google Scholar PubMed
[16] G. E. Christensen, S. C. Joshi and M. I. Miller, Volumetric transformation of brain anatomy, IEEE Trans. Med. Imaging 16 (1997), no. 6, 864–877. 10.1109/42.650882Search in Google Scholar PubMed
[17] G. E. Christensen, J. H. Song, W. Lu, I. El Naqa and D. A. Low, Tracking lung tissue motion and expansion/compression with inverse consistent image registration and spirometry, Med. Phys. 34 (2007), no. 6, 2155–2163. 10.1118/1.2731029Search in Google Scholar PubMed
[18] N. Chumchob and K. Chen, A robust affine image registration method, Int. J. Numer. Anal. Model. 6 (2009), no. 2, 311–334. Search in Google Scholar
[19] N. Chumchob and K. Chen, A robust multigrid approach for variational image registration models, J. Comput. Appl. Math. 236 (2011), no. 5, 653–674. 10.1016/j.cam.2011.06.026Search in Google Scholar
[20] N. Chumchob, K. Chen and C. Brito-Loeza, A fourth-order variational image registration model and its fast multigrid algorithm, Multiscale Model. Simul. 9 (2011), no. 1, 89–128. 10.1137/100788239Search in Google Scholar
[21] B. Dacorogna, Direct Methods in the Calculus of Variations, Appl. Math. Sci. 78, Springer, Berlin, 1989. 10.1007/978-3-642-51440-1Search in Google Scholar
[22] O. Demetz, M. Stoll, S. Volz, J. Weickert and A. Bruhn, Learning brightness transfer functions for the joint recovery of illumination changes and optical flow, Computer Vision – ECCV 2014, Lecture Notes in Comput. Sci. 8689, Springer, Cham (2014), 455–471. 10.1007/978-3-319-10590-1_30Search in Google Scholar
[23] C. Frohn-Schauf, S. Henn, L. Hömke and K. Witsch, Total variation based image registration, Image Processing Based on Partial Differential Equations, Math. Vis., Springer, Berlin (2007), 343–361. 10.1007/s00791-007-0060-2Search in Google Scholar
[24] C. Frohn-Schauf, S. Henn and K. Witsch, Multigrid based total variation image registration, Comput. Vis. Sci. 11 (2008), no. 2, 101–113. 10.1007/s00791-007-0060-2Search in Google Scholar
[25] A. Gooya, G. Biros and C. Davatzikos, Deformable registration of glioma images using em algorithm and diffusion reaction modelling, IEEE Trans. Med. Imaging 30 (2011), no. 2, 375–390. 10.1109/TMI.2010.2078833Search in Google Scholar PubMed PubMed Central
[26] V. Gorbunova, J. Sporring, P. Lo, M. Loeve, H. A. Tiddens, M. Nielsen, A. Dirksen and M. de Bruijne, Mass preserving image registration for lung CT, Med. Image Anal. 16 (2012), no. 4, 786–795. 10.1016/j.media.2011.11.001Search in Google Scholar PubMed
[27] N. M. Grosland, R. Bafna and V. A. Magnotta, Automated hexahedral meshing of anatomic structures using deformable registration, Comp. Meth. Biomech. Biomed. Eng. 12 (2009), no. 1, 35–43. 10.1080/10255840802136143Search in Google Scholar
[28] T. Guerro, K. Sanders, E. Castillo, Y. Zhang, L. Bidaut, T. Pan and R. Komaki, Dynamic ventillation imaging from four-dimensional computed tomography, Phys. Med. Biol. 51 (2006), no. 4, 777–791. 10.1088/0031-9155/51/4/002Search in Google Scholar PubMed
[29] C. Guetter, H. Xue, C. Chefd’hotel and J. Guehring, Efficient symmetric and inverse-consistent deformable registration through inter-leaved optimization, Biomedical Imaging: From Nano to Macro, IEEE Press, Piscataway (2011), DOI 10.1109/ISBI.2011.5872476. 10.1109/ISBI.2011.5872476Search in Google Scholar
[30] E. Haber and J. Modersitzki, A multilevel method for image registration, SIAM J. Sci. Comput. 27 (2006), no. 5, 1594–1607. 10.1137/040608106Search in Google Scholar
[31] S. Henn, A multigrid method for a fourth-order diffusion equation with application to image processing, SIAM J. Sci. Comput. 27 (2005), no. 3, 831–849. 10.1137/040611124Search in Google Scholar
[32] S. Henn and K. Witsch, Iterative multigrid regularization techniques for image matching, SIAM J. Sci. Comput. 23 (2001), no. 4, 1077–1093. 10.1137/S106482750037161XSearch in Google Scholar
[33] D. L. G. Hill, P. G. Batchelor, M. Holden and D. J. Hawkes, Medical image registration, Phys. Med. Biol. 46 (2001), no. 3, 1–45. 10.1088/0031-9155/46/3/201Search in Google Scholar PubMed
[34] H. J. Johnson and G. E. Christensen, Consistent landmark and intensity-based image registration, IEEE Trans. Med. Imaging 21 (2002), no. 5, 450–461. 10.1109/TMI.2002.1009381Search in Google Scholar PubMed
[35] H. Köstler, K. Ruhnau and R. Wienands, Multigrid solution of the optical flow system using a combined diffusion- and curvature-based regularizer, Numer. Linear Algebra Appl. 15 (2008), no. 2–3, 201–218. 10.1002/nla.576Search in Google Scholar
[36] K. C. Lam and L. M. Lui, Landmark- and intensity-based registration with large deformations via quasi-conformal maps, SIAM J. Imaging Sci. 7 (2014), no. 4, 2364–2392. 10.1137/130943406Search in Google Scholar
[37] Y. T. Lee, K. C. Lam and L. M. Lui, Landmark-matching transformation with large deformation via n-dimensional quasi-conformal maps, J. Sci. Comput. 67 (2016), no. 3, 926–954. 10.1007/s10915-015-0113-5Search in Google Scholar
[38] T. Lin, C. Le Guyader, I. Dinov, P. Thompson, A. Toga and L. Vese, Gene expression data to mouse atlas registration using a nonlinear elasticity smoother and landmark points constraints, J. Sci. Comput. 50 (2012), no. 3, 586–609. 10.1007/s10915-011-9563-6Search in Google Scholar PubMed PubMed Central
[39] J. Modersitzki, Numerical Methods for Image Registration, Math. Sci. Comput., Oxford University Press, New York, 2004. 10.1093/acprof:oso/9780198528418.001.0001Search in Google Scholar
[40] J. Modersitzki, FAIR: Flexible Algorithms for Image Registration, Fundam. Algorithms 6, Society for Industrial and Applied Mathematics (SIAM), Philadelphia, 2009. 10.1137/1.9780898718843Search in Google Scholar
[41] A. Pevsner, B. Davis, S. Joshi, A. Hertanto, J. Mechalakos, E. Yorke, K. Rosenzweig, S. Nehmeh, Y. E. Erdi, J. L. Humm, S. Larson, C. C. Ling and G. S. Mageras, Evaluation of an automated deformable image matching method for quantifying lung motion in respiration-correlated ct images, Med. Phys. 33 (2006), no. 2, 369–376. 10.1118/1.2161408Search in Google Scholar PubMed
[42]
T. Pock, M. Urschler, C. Zach, R. Beichel and H. Bischof,
A duality based algorithm for TV-
[43] M. Reuter, H. Rosas and B. Bacth Fischl, Highly accurate inverse consistent registration: A robust approach, Neuroimage 53 (2010), no. 4, 1181–1196. 10.1016/j.neuroimage.2010.07.020Search in Google Scholar PubMed PubMed Central
[44] L. Ruthotto, C. Greif and J. Modersitzki, A stabilized multigrid solver for hyperelastic image registration, Numer. Linear Algebra Appl. 24 (2017), no. 5, Article ID e2095. 10.1002/nla.2095Search in Google Scholar
[45] D. Sarrut, V. Boldea, S. Miguet and C. Ginestet, Simulation of four-dimensional ct images from deformable registration between inhale and exhale breath-hold ct scans, Med. Phys. 33 (2006), no. 3, 605–617. 10.1118/1.2161409Search in Google Scholar PubMed
[46] U. Trottenberg, C. W. Oosterlee and A. Schüller, Multigrid, Academic Press, San Diego, 2001. Search in Google Scholar
[47] R. Wienands and W. Joppich, Practical Fourier Analysis for Multigrid Methods, Numer. Insights 4, Chapman & Hall/CRC, Boca Raton, 2005. 10.1201/9781420034998Search in Google Scholar
[48] D. Yang, H. Li, D. A. Low, J. O. Deasy and I. El Naqa, A fast inverse consistent deformable image registration method based on symmetric optical flow computation, Phys. Med. Biol. 53 (2008), no. 21, 6143–6165. 10.1109/ACSSC.2008.5074766Search in Google Scholar
[49] D. Zhang and K. Chen, A novel diffeomorphic model for image registration and its algorithm, J. Math. Imaging Vision 60 (2018), no. 8, 1261–1283. 10.1007/s10851-018-0811-3Search in Google Scholar
© 2021 Walter de Gruyter GmbH, Berlin/Boston
