Abstract
This paper proposes ℒ2- and information-theory-based (IT) non-rigid registration algorithms that are exactly symmetric. Such algorithms pair the same points of two images after the images are swapped. Many commonly-used ℒ2 and IT non-rigid registration algorithms are only approximately symmetric. The asymmetry is due to the objective function as well as due to the numerical techniques used in discretizing and minimizing the objective function. This paper analyzes and provides techniques to eliminate both sources of asymmetry.
This paper has five parts. The first part shows that objective function asymmetry is due to the use of standard differential volume forms on the domain of the images. The second part proposes alternate volume forms that completely eliminate objective function asymmetry. These forms, called graph-based volume forms, are naturally defined on the graph of the registration diffeomorphism f, rather than on the domain of f. When pulled back to the domain of f they involve the Jacobian J f and therefore appear “non-standard”. In the third part of the paper, graph-based volume forms are analyzed in terms of four key objective-function properties: symmetry, positive-definiteness, invariance, and lack of bias. Graph-based volume forms whose associated ℒ2 objective functions have the first three properties are completely classified. There is an infinite-dimensional space of such graph-based forms. But within this space, up to scalar multiple, there is a unique volume form whose associated ℒ2 objective function is unbiased. This volume form, which when pulled back to the domain of f is (1+det(J f )) times the standard volume form on Euclidean space, is exactly the differential-geometrically natural volume form on the graph of f. The fourth part of the paper shows how the same volume form also makes the IT objective functions symmetric, positive semi-definite, invariant, and unbiased. The fifth part of the paper introduces a method for removing asymmetry in numerical computations and presents results of numerical experiments. The new objective functions and numerical method are tested on a coronal slice of a 3-D MRI brain image. Numerical experiments show that, even in the presence of noise, the new volume form and numerical techniques reduces asymmetry practically down to machine precision without compromising registration accuracy.
Similar content being viewed by others
References
Hajnal, J.V., Hill, D.L.G., Hawkes, D.J.: Medical Image Registration. CRC Press, Boca Raton (2001)
Toga, A.: Brain Warping. Academic Press, San Diego (1999)
Goshtaby, A.A.: 2-D and 3-D Image Registration for Medical Remote Sensing and Industrial Applications. Wiley, Hoboken (2005)
Maintz, J.B.A., Viergever, M.A.: A survey of image registration. Med. Image Anal. MEDIA 2(1), 1–36 (1998)
Zitová, B., Flusser, J.: Image registration methods: a survey. Image Vis. Comput. 21(11), 977–1000 (2003)
Pluim, J.P.W., Maintz, J.B.A., Viergever, M.A.: Mutual information based registration of medical images: a survey. IEEE Trans. Med. Imag. 22(8), 986–1004 (2003)
Christensen, G.E., Johnson, H.J.: Consistent image registration. IEEE Trans. Med. Imag. 20(7), 568–582 (2001)
Johnson, H.J., Christensen, G.E.: Consistent landmark and intensity-based image registration. IEEE Trans. Med. Imag. 21(5), 450–461 (2002)
Christensen, G.E., Johnson, H.J.: Invertibility and transitivity analysis for non-rigid image registration. J. Electron. Imag. 12(1), 106–117 (2003)
Ashburner, J., Andersson, J.L.R., Friston, K.J.: High-dimensional image registration using symmetric prior. NeuroImage 9(6), 619–628 (1999)
Beg, M.F., Khan, A.: Symmetric data attachment terms for large deformation image registration. IEEE Trans. Med. Imag. 26(9), 1179–1189 (2007)
Cachier, P., Rey, D.: Symmetrization of the non-rigid registration problem using inversion-invariant energies: application to multiple sclerosis. In: Medical Image Computing and Computer Aided Intervention (MICCAI), Pittsburgh, PA, October 2000, pp. 472–481
Rogelj, P., Kovacic, S.: Symmetric image registration. Med. Image Anal. 10(3), 484–493 (2006)
Joshi, S., Davis, B., Jomier, M., Gerig, G.: Unbiased diffeomorphic atlas construction for computational anatomy. NeuroImage 23(1), S151–S160 (2004). Supplement issue on Mathematics in Brain Imaging
Lorenzen, P., Prastawa, M., Davis, B., Gerig, G., Bullitt, E., Joshi, S.: Multi-modal image set registration and atlas formation. Med. Image Anal. MEDIA 10(3), 440–451 (2006)
Avants, B.B., Epstein, C.L., Grossman, M., Gee, J.C.: Symmetric diffeomorphic image registration with cross-correlation: Evaluating automated labeling of elderly and neurodegenerative brain. Med. Image Anal. 12(1), 26–41 (2008)
Tagare, H.D., O’Shea, D., Groisser, D.: Shape based non-rigid correspondence for plane curves. J. Math. Imag. Vis. 16, 57–68 (2002)
Tagare, H.D.: Shape-based non-rigid correspondence with applications to heart motion analysis. IEEE Trans. Med. Imag. 18(7), 570–579 (1999)
Lorenzen, P., Davis, B., Joshi, S.: Model based symmetric information theoretic large deformation multi-model image registration. In: Intl. Symp. Biomedical Imaging, pp. 720–723 (2004)
Lorenzen, P., Davis, B., Joshi, S.: Unbiased atlas formation via large deformations metric mapping. In: J.S. Duncan, G. Gerig (eds.) Medical Image Computing and Computer Assisted Intervention (MICCAI), pp. 411–418 (2005)
Magnotta, V.A., Bockholt, H.J., Johnson, H.J., Christensen, G.E., Andreasen, N.C.: Subcortical, cerebellar and MR based consistent brain image registration. NeuroImage 19(2), 233–245 (2003)
Christensen, G.E., Johnson, H.J., Vannier, M.W.: Synthesizing average 3D anatomical shapes. NeuroImage 32, 146–158 (2006)
Li, B., Christensen, G.E., McLennan, G., Hoffman, E.A., Reinhardt, J.M.: Establishing a normative atlas of the human lung: Inter-subject warping and registration of volumetric CT. Acad. Radiology 10(3), 255–265 (2003)
Lu, W., Parikh, P., El Naqa, I., Nystrom, M., Hubenschmidt, J., Wahab, S., Mutic, S., Sing, A., Christensen, G.E., Bradley, J.D., Low, D.A.: Quantitation of the four-dimensional computed tomography process for lung cancer patients. Med. Phys. 32(4), 890–901 (2005)
Christensen, G.E., He, J., Dill, J.A., Rubinstein, J.T., Vannier, M.W., Wang, G.: Automatic measurement of the labyrinth using image registration and a deformable inner ear atlas. Acad. Radiology 10(9), 988–999 (2003)
Wells, W.M. III, Viola, P., Atsumi, H., Nakajima, S., Kikinis, R.: Multi-modal volume registration by maximization of mutual information. Med. Image Anal. 1(1), 35–51 (1996)
Studholme, C., Hill, D.L.G., Hawkes, D.J.: An overlap invariant entropy measure of 3D medical image alignment. Pattern Recognit. 32(1), 71–86 (1999)
Viola, P., Wells, W.M. III: Alignment by maximization of mutual information. Int. J. Comput. Vis. 24(2), 137–154 (1997)
D’Agostino, E., Maes, F., Vandermeulen, D., Suetens, P.: A viscous fluid model for multimodal non-rigid image registration using mutual information. Med. Image Anal. 7, 565–575 (2003)
Pluim, J.P.W., Maintz, J.B.A., Viergever, M.A.: F-information measures in medical image registration. IEEE Trans. Med. Imag. 23(12), 1508–1516 (2004)
Yanovsky, I., Thompson, P., Osher, S., Leow, A.: Topology preserving log-unbiased non-linear image registration: theory and implementation. In: IEEE Conf. on Computer Vision and Pattern Recognition, June 2007
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Tagare, H.D., Groisser, D. & Skrinjar, O. Symmetric Non-rigid Registration: A Geometric Theory and Some Numerical Techniques. J Math Imaging Vis 34, 61–88 (2009). https://doi.org/10.1007/s10851-008-0129-7
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10851-008-0129-7