Abstract
This paper introduces Fourier-approximated Lie algebras for shooting (FLASH), a fast geodesic shooting algorithm for diffeomorphic image registration. We approximate the infinite-dimensional Lie algebra of smooth vector fields, i.e., the tangent space at the identity of the diffeomorphism group, with a low-dimensional, bandlimited space. We show that most of the computations for geodesic shooting can be carried out entirely in this low-dimensional space. Our algorithm results in dramatic savings in time and memory over traditional large-deformation diffeomorphic metric mapping algorithms, which require dense spatial discretizations of vector fields. To validate the effectiveness of FLASH, we run pairwise image registration on both 2D synthetic data and real 3D brain images and compare with the state-of-the-art geodesic shooting methods. Experimental results show that our algorithm dramatically reduces the computational cost and memory footprint of diffemorphic image registration with little or no loss of accuracy.









Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Notes
Since a circular convolution between two bandlimited signals does not preserve the bandlimit, we define a convolution operation on zero-padded signals by truncating the output back to the bandlimits, \(n_i\), in each dimension to guarantee the Lie bracket is closed.
References
Arnol’d, V. I. (1966). Sur la géométrie différentielle des groupes de Lie de dimension infinie et ses applications à l’hydrodynamique des fluides parfaits. Ann Inst Fourier, 16, 319–361.
Arsigny, V., Commowick, O., Pennec, X., & Ayache, N. (2006). A log-Euclidean framework for statistics on diffeomorphisms. In Medical image computing and computer-assisted intervention—MICCAI 2006, Springer (pp. 924–931).
Ashburner, J. (2007). A fast diffeomorphic image registration algorithm. Neuroimage, 38(1), 95–113.
Ashburner, J., & Friston, K. J. (2011). Diffeomorphic registration using geodesic shooting and Gauss–Newton optimisation. NeuroImage, 55(3), 954–967.
Beg, M., Miller, M., Trouvé, A., & Younes, L. (2005). Computing large deformation metric mappings via geodesic flows of diffeomorphisms. International Journal of Computer Vision, 61(2), 139–157.
Bullo, F. (1995). Invariant affine connections and controllability on Lie groups. Technical Report for Geometric Mechanics, California Institute of Technology.
Christensen, G. E., Rabbitt, R. D., & Miller, M. I. (1996). Deformable templates using large deformation kinematics. IEEE Transactions on Image Processing, 5(10), 1435–1447.
Dupuis, P., Grenander, U., & Miller, M. I. (1998). Variational problems on flows of diffeomorphisms for image matching. Quarterly of Applied Mathematics, 56(3), 587.
Durrleman, S., Prastawa, M., Gerig, G., & Joshi, S. (2011). Optimal data-driven sparse parameterization of diffeomorphisms for population analysis. In Information processing in medical imaging, Springer (pp. 123–134).
Hinkle, J., Fletcher, P. T., & Joshi, S. (2014). Intrinsic polynomials for regression on Riemannian manifolds. Journal of Mathematical Imaging and Vision, 50(1–2), 32–52.
Hromatka, M., Zhang, M., Fleishman, G. M., Gutman, B., Jahanshad, N., Thompson, P., & Fletcher, P. T. (2015). A hierarchical Bayesian model for multi-site diffeomorphic image atlases. In Medical image computing and computer-assisted intervention—MICCAI 2015, Springer (pp. 372–379).
Joshi, S., Davis, B., Jomier, M., & Gerig, G. (2004). Unbiased diffeomorphic atlas construction for computational anatomy. NeuroImage, 223(Supplement 1), 151–160.
Marcus, D. S., Wang, T. H., Parker, J., Csernansky, J. G., Morris, J. C., & Buckner, R. L. (2007). Open access series of imaging studies (OASIS): Cross-sectional mri data in young, middle aged, nondemented, and demented older adults. Journal of Cognitive Neuroscience, 19(9), 1498–1507.
Miller, M. I., Trouvé, A., & Younes, L. (2006). Geodesic shooting for computational anatomy. Journal of Mathematical Imaging and Vision, 24(2), 209–228. https://doi.org/10.1007/s10851-005-3624-0.
Niethammer, M., Huang, Y., & Vialard, F. X. (2011). Geodesic regression for image time-series. In International conference on medical image computing and computer-assisted intervention, Springer (pp. 655–662).
Singh, N., Hinkle, J., Joshi, S., & Fletcher, P. T. (2013). A vector momenta formulation of diffeomorphisms for improved geodesic regression and atlas construction. In International symposium on biomedial imaging (ISBI).
Trouvé, A. (1998). Diffeomorphisms groups and pattern matching in image analysis. International Journal of Computer Vision, 28(3), 213–221.
Vaillant, M., Miller, M. I., Younes, L., & Trouvé, A. (2004). Statistics on diffeomorphisms via tangent space representations. NeuroImage, 23, S161–S169.
Vercauteren, T., Pennec, X., Perchant, A., & Ayache, N. (2009). Diffeomorphic demons: Efficient non-parametric image registration. NeuroImage, 45(1), S61–S72.
Vialard, F. X., Risser, L., Rueckert, D., & Cotter, C. J. (2012). Diffeomorphic 3D image registration via geodesic shooting using an efficient adjoint calculation. International Journal of Computer Vision, 97(2), 229–241.
Younes, L., Arrate, F., & Miller, M. (2009). Evolutions equations in computational anatomy. NeuroImage, 45(1S1), 40–50.
Zhang, M., & Fletcher, P. T. (2014). Bayesian principal geodesic analysis in diffeomorphic image registration. In Medical image computing and computer-assisted intervention–MICCAI 2014, Springer (pp. 121–128).
Zhang, M., & Fletcher, P. T. (2015). Finite-dimensional Lie algebras for fast diffeomorphic image registration. In Information processing in medical imaging.
Zhang, M., Liao, R., Dalca, A. V., Turk, E. A., Luo, J., Grant, P. E., & Golland, P. (2017). Frequency diffeomorphisms for efficient image registration. In International conference on information processing in medical imaging, Springer (pp. 559–570).
Zhang, M., Singh, N., & Fletcher, P. T. (2013). Bayesian estimation of regularization and atlas building in diffeomorphic image registration. J. C. Gee, S. Joshi, K. M. Pohl, W. M. Wells & L. Zöllei (Eds.), Information processing in medical imaging (pp. 37–48). Springer.
Zhang, M., Wells III, W. M., & Golland, P. (2016). Low-dimensional statistics of anatomical variability via compact representation of image deformations. In International conference on medical image computing and computer-assisted intervention, Springer (pp. 166–173).
Acknowledgements
This work was supported by NIH Grant 5R01EB007688 and NSF CAREER Grant 1054057.
Author information
Authors and Affiliations
Corresponding author
Additional information
Communicated by Daniel Cremers.
Appendix A
Appendix A
1.1 Properties of truncated convolution
We compute the truncated convolution in a bandlimited space by padding a sufficient number of zeros, \(n_i-1\), at the end of each dimension, and then truncate the signal back to its original space. Note that (1) the convolution is modulo-\(q_i\) (\(q_i = 2n_i-1\)) circular convolution, (2) the zero frequency component is shifted to the center of the domain.
We first introduce the kth element of a truncated convolution of any tangent vector field \(\tilde{v}, \tilde{w} \in \tilde{V}\) as
where \(l=(l_1, \ldots , l_d)\in \mathbb {Z}^d\) are the padded frequency indices with \(l_i \in \{0, \ldots , q_i\}\) along the ith axis. Let \(M_i = \lfloor \frac{n_i-1}{2}\rfloor \), then \(k=(k_1, \ldots , k_d) \in \mathbb {Z}^d\) denotes truncated frequency indexes with \(k_i \in \{ M_{i}, \ldots , M_i + n_i - 1\}\). Notice here the \(k-l\) represents \(k-l\,(\mathrm{mod}\,q)\) with cyclic boundary conditions, and the vector field \(\tilde{v}\) can also be replaced with a matrix field.
We then prove the commutativity and associativity of this truncated convolution. For any \(\tilde{u}, \tilde{v}, \tilde{w} \in \tilde{V}\),
-
Commutativity: \(\tilde{u} *\tilde{v}= \tilde{v} *\tilde{u}\)
Proof
The kth element of \(\tilde{u} *\tilde{v}\) is
By changing the coordinates using \(k-l=k'\) where \(k \in [M, M+n-1]\) and \(k' \in [0, q]\) due to the cyclic condition, we rewrite the equation above as
\(\square \)
-
Associativity: \((\tilde{u} *\tilde{v}) *\tilde{w} = \tilde{u} *(\tilde{v} *\tilde{w})\)
Proof
The kth element of \((\tilde{u} *\tilde{v}) *\tilde{w}\) is
where \(k \in [M, M+n-1]\). We then rewrite the equation above by changing the coordinates using \(k-l'-l=a\), where \(a \in [0, q]\), as
\(\square \)
1.2 Deriving \(\mathrm{ad}^*\) operator
Before showing the derivation of \(\mathrm{ad}^*\) in a bandlimited space, we first introduce the pairing between a result of the truncated convolution (18) and a momentum vector field \(\tilde{m} \in \tilde{V}^*\) is
We are now ready to derive the \(\mathrm{ad}^*\) operator from its definition
Since \(\mathrm{ad}_{\tilde{v}} \tilde{w} = [\tilde{v}, \tilde{w}]\), after plugging in the definition of Lie bracket defined in (10) we have
To separate \(\tilde{w}\), we change coordinates by defining \(k-M=k'\), \(l-M=l'\) where \(k' \in [0, n-1]\) and \(l' \in [-M, q-M]\). For the purpose of notation simplicity, we drop the range of variables in the following equations as
Finally, we have
Rights and permissions
About this article
Cite this article
Zhang, M., Fletcher, P.T. Fast Diffeomorphic Image Registration via Fourier-Approximated Lie Algebras. Int J Comput Vis 127, 61–73 (2019). https://doi.org/10.1007/s11263-018-1099-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11263-018-1099-x