Abstract
The family of PDE-constrained Large Deformation Diffeomorphic Metric Mapping (LDDMM) methods is emerging as a particularly interesting approach for physically meaningful diffeomorphic transformations. The original combination of Gauss–Newton–Krylov optimization and Runge–Kutta integration shows excellent numerical accuracy and fast convergence rate. However, its most significant limitation is the huge computational complexity, hindering its extensive use in Computational Anatomy applied studies. This limitation has been treated independently by the problem formulation in the space of band-limited vector fields and semi-Lagrangian integration. The purpose of this work is to combine both in three variants of band-limited PDE-constrained LDDMM for further increasing their computational efficiency. The accuracy of the resulting methods is evaluated extensively. For all the variants, the proposed combined approach shows a significant increment of the computational efficiency. In addition, the variant based on the deformation state equation is positioned consistently as the best performing method across all the evaluation frameworks in terms of accuracy and efficiency.
Similar content being viewed by others
Abbreviations
- PDE:
-
Partial differential equation
- LDDMM:
-
Large deformation diffeomorphic metric mapping
- SP:
-
Spatial
- BL:
-
Band limited
- RK:
-
Runge–Kutta
- SL:
-
Semi-Lagrangian
- PCG:
-
Preconditioned conjugate gradient
- DSC:
-
Dice similarity coefficient
- SSD:
-
Sum of squared differences
- CPU:
-
Central processing unit
- GPU:
-
Graphics processing unit
- VRAM:
-
Video random access memory
References
Ashburner, J., Friston, K.J.: Diffeomorphic registration using geodesic shooting and Gauss–Newton optimisation. Neuroimage 55(3), 954–967 (2011)
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, 26–41 (2008)
Beg, M.F., Miller, M.I., Trouve, A., Younes, L.: Computing large deformation metric mappings via geodesic flows of diffeomorphisms. Int. J. Comput. Vis. 61(2), 139–157 (2005)
Brunn, M., Himthani, N., Biros, G., Mehl, M.: Fast gpu 3d diffeomorphic image registration. ArXiv (2020)
Dosovitskiy, A., Fischer, P., Ilg, E., Hausser, P., Hazirbas, C., Golkov, V., v.d. Smagt, P., Cremers, D., Brox, T.: FlowNet: learning optical flow with convolutional networks (2015)
Guo, D.X.: A Semi-Lagrangian Runge–Kutta method for time-dependent partial differential equations. J. Appl. Anal. Comput. 3(3), 251–263 (2013)
Hart, G.L., Zach, C., Niethammer, M.: An optimal control approach for deformable registration. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’09) (2009)
Hernandez, M.: Band-limited stokes large deformation diffeomorphic metric mapping. IEEE J. Biomed. Health Inform. 23(1), 362–373 (2019)
Hernandez, M.: A comparative study of different variants of Newton–Krylov PDE-constrained Stokes-LDDMM parameterized in the space of band-limited vector fields. SIAM J. Imaging Sci. 12, 1038–1070 (2019)
Hernandez, M.: PDE-constrained LDDMM via geodesic shooting and inexact Gauss–Newton–Krylov optimization using the incremental adjoint Jacobi equations. Phys. Med. Biol. 64(2), 025002 (2019)
Hernandez, M., Bossa, M.N., Olmos, S.: Registration of anatomical images using paths of diffeomorphisms parameterized with stationary vector field flows. Int. J. Comput. Vis. 85(3), 291–306 (2009)
Klein, A., et al.: Evaluation of 14 nonlinear deformation algorithms applied to human brain MRI registration. Neuroimage 46(3), 786–802 (2009)
Mang, A., Biros, G.: An inexact Newton–Krylov algorithm for constrained diffeomorphic image registration. SIAM J. Imaging Sci. 8(2), 1030–1069 (2015)
Mang, A., Biros, G.: Constrained H1 regularization schemes for diffeomorphic image registration. SIAM J. Imaging Sci. 9(3), 1154–1194 (2016)
Mang, A., Biros, G.: A semi-Lagrangian two-level preconditioned Newton–Krylov solver for constrained diffeomorphic image registration. SIAM J. Sci. Comput. 39(6), B1064–B1101 (2017)
Mang, A., Gholami, A., Biros, G.: Distributed-memory large-deformation diffeomorphic 3D image registration. In: Proceedings of ACM/IEEE Super Computing conference (SC16) (2016)
Mang, A., Gholami, A., Davatzikos, C., Biros, G.: Claire: a distributed-memory solver for constrained large deformation diffeomorphic image registration. SIAM J. Sci. Comput. 41(5), C548–C584 (2019)
Mang, A., Ruthotto, L.: A Lagrangian Gauss–Newton–Krylov solver for mass- and intensity-preserving diffeomorphic image registration. SIAM J. Sci. Comput. 39(5), B860–B885 (2017)
Miller, M.I.: Computational anatomy: shape, growth, and atrophy comparison via diffeomorphisms. Neuroimage 23, 19–33 (2004)
Miller, M.I., Qiu, A.: The emerging discipline of computational functional anatomy. Neuroimage 45(1), 16–39 (2009)
Modersitzki, J.: FAIR: Flexible Algorithms for Image Registration. SIAM, Philadelphia (2009)
Polzin, T., Niethammer, M., Heinrich, M.P., Handels, H., Modersitzki, J.: Memory efficient LDDMM for lung CT. In: Proc. of the 19th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI’16), Lecture Notes in Computer Science, pp. 28–36 (2014)
Ramon-Julvez, U., Hernandez, M., Mayordomo, E., ADNI: Analysis of the influence of diffeomorphic normalization in the prediction of stable vs progressive MCI conversion with convolutional neural networks. In: Proceedings of the 17th IEEE International Symposium on Biomedical Imaging: From Nano to Macro (ISBI’20) (2020)
Riishojgaard, L.P., Cohn, S.E., Li, Y., Menard, R.: The use of spline interpolation in semi-Lagrangian transport models. Mon. Weather Rev. 126(7), 2008–2016 (1998)
Rohlfing, T.: Image similarity and tissue overlaps as surrogates for image registration accuracy: widely used but unreliable. IEEE Trans. Med. Imaging 31(2), 153–163 (2012)
Ruijters, D., Thevenaz, P.: GPU prefilter for accurate cubic B-spline interpolation. Comput. J. 55(1), 15–20 (2012)
Schiratti, J.B., Allassonniere, S., Colliot, O., Durrleman, S.: Learning spatiotemporal trajectories from manifold-valued longitudinal data. Adv. Neural Inf. Process. Syst. 28, 2404–2412 (2015)
Shen, Z., Vialard, F.X., Niethammer, M.: Region-specific diffeomorphic metric mapping. In: Advances in Neural Information Processing Systems (NIPS 2019) (2019)
Sotiras, A., Davatzikos, C., Paragios, N.: Deformable medical image registration: a survey. IEEE Trans. Med. Imaging 32(7), 1153–1190 (2013)
Staniforth, A., Cote, J.: Semi-Lagrangian integration schemes for atmospheric models—a review. Mon. Weather Rev. 119, 2206–2223 (1991)
Thompson, D.W.: On Growth and Form. Cambridge University Press, Cambridge (1917)
Vialard, F.X., Risser, L., Rueckert, D., Cotter, C.J.: Diffeomorphic 3D image registration via geodesic shooting using an efficient adjoint calculation. Int. J. Comput. Vis. 97(2), 229–241 (2011)
Younes, L.: Jacobi fields in groups of diffeomorphisms and applications. Q. Appl. Math. 65, 113–134 (2007)
Younes, L.: Shapes and Diffeomorphisms. Springer, Berlin (2010)
Zhang, M., Fletcher, P.T.: Finite-dimensional Lie algebras for fast diffeomorphic image registration. In: Proceedings of International Conference on Information Processing and Medical Imaging (IPMI’15), Lecture Notes in Computer Science (2015)
Zhang, M., Fletcher, T.: Fast diffeomorphic image registration via Fourier-Approximated Lie algebras. Int. J. Comput. Vis. 127, 61–73 (2018)
Acknowledgements
The author would like to acknowledge the anonymous reviewers for their valuable revision of the manuscript. The author would like to give special thanks to Wen Mei Hwu from the University of Illinois for interesting ideas in the GPU implementation of the methods, and Nacho Navarro and Rosa Badia from the Barcelona Supercomputing Center (BSC) for their help. This work was partially supported by the National Research Grant TIN2016-80347-R (DIAMOND Project), PID2019-104358RB-I00 (DL-Aging Project), and Government of Aragon Group Reference \(T64\_20R\) (COS2MOS research group). In addition, this work was supported by NVIDIA through the Polytechnical University of Catalonia/Barcelona Supercomputing Center (UPC/BSC) GPU Center of Excellence.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
This work was partially supported by the National Research Grants PID2019-104358RB-I00 (DL-Aging Project) and TIN2016-80347-R (DIAMOND Project)
Appendix
Appendix
Appendix gathers the expressions of the gradient and the Hessian for the PDE-LDDMM variants defined in the spatial domain and the method for SL-RK integration.
1.1 A.1 Original PDE-Constrained LDDMM (Variant I)
Let E(v) be the PDE-constrained variational problem given in Eq. 4. Let us define the Lagrange multipliers \(\lambda :\varOmega \times [0,1] \rightarrow \mathbb {R}\) and \(\eta :\varOmega \rightarrow \mathbb {R}\) associated with the state equation (Eq. 5) and its initial condition. The augmented Lagrangian corresponds with the expression
The first- and second-order optimality conditions are derived from the formal computations of
and
The details of the formal derivations can be found in [9].
Since \(\delta E_\text {aug}\) needs to vanish for any dv, dm, and \(d\eta \), we get the necessary first-order optimality conditions for Variant I. In particular, the expression of the gradient is given by
where m and \(\lambda \) are computed from the state and the adjoint equations
with their corresponding initial conditions \(m(0) = I_0\) and \(\lambda (1) = -\frac{2}{\sigma ^2}(m(1)-I_1)\).
The necessary second-order optimality conditions are obtained vanishing \(\delta ^2 E_\text {aug}\) for any dv, dm, and \(d\eta \). Thus, the Gauss–Newton approximation of the Hessian vector product is given by
where \(\delta \lambda \) is computed from the incremental adjoint equation
with initial condition \(\delta \lambda (1) = -\frac{2}{\sigma ^2} \delta m(1)\), where \(\delta m(1)\) is computed from the incremental state equation
with initial condition \(\delta m(0) = 0\).
1.2 A.2 PDE-Constrained LDDMM Based on the State Equation (Variant II)
Variant II consists in replacing the computation of the state and the adjoint variables, m and \(\lambda \), from the solution of the state and adjoint PDEs to the identities \(m(t) = I_0 \circ \phi (t)\) and \(\lambda (t) = J(t) \lambda (1) \circ \psi (t)\), where \(\phi (t)\) is the direct map, \(\psi (t)\) is the inverse map, and J is the Jacobian determinant of \(\psi \). As a result, Variants I and II are two theoretically but not numerically equivalent formulations of the original PDE-LDDMM problem.
For Variant II, the derivation of the gradient and the Hessian vector product proceeds as for Variant I. However, the computation of the state and adjoint variables is performed using their identities, transferring PDE resolution to the deformation state equation for \(\phi \) and \(\psi \)
with initial condition \(\phi (0) = id\) and \(\psi (1) = id\), and the Jacobian equation for J
with initial condition \(J(1)=1\). The incremental state and adjoint variables are computed from the incremental expression of the identities
and, again, the PDE resolution is transferred to the incremental deformation state equations for \(\delta \phi \) and \(\delta \psi \)
1.3 A.3 PDE-Constrained LDDMM Based on the Deformation State Equation (Variant III)
For Variant III, the Lagrange multipliers are \(\rho :\varOmega \times [0,1] \rightarrow \mathbb {R}^d\), associated with the deformation state equation (Eq. 7), and \(\mu :\varOmega \rightarrow \mathbb {R}^d\), associated with its initial condition. The augmented Lagrangian corresponds with
The first- and second-order optimality conditions are derived from the formal computations of
and
The necessary first- and second-order optimality conditions are obtained from the need to vanish \(\delta E_\text {aug}\) and \(\delta ^2 E_\text {aug}\) for any dv, \(d\phi \), \(d\rho \), and \(d\mu \), yielding
where \(\phi \) is computed from the deformation state equation, \(\rho \) from the deformation adjoint equation, and \(\delta \rho \) from the incremental deformation adjoint equation
with initial conditions \(\phi (0) = id\), \(\rho (1) = \lambda (1) \nabla m(1)\), \(\delta \rho (1) = \delta \lambda (1) \nabla m(1)\). It should be noticed that the divergence operator acting on tensors operates row-wise.
1.4 A.4 Semi-Lagrangian Runge–Kutta Integration
As we mentioned in Sect. 3, to be able to apply SL integration, the differential equations for different spatial variants need to be written in the shape of Eq. 46. The state equations, the deformation state equations, and their incremental counterparts (Eqs. 57, 62, 61, 67) are already in the shape of Eq. 46 by just moving to the right-hand side of the equation a remaining term. For the adjoint and the incremental adjoint equations (Eqs. 58, 74, 60, 75), we use the identity
and move the divergence term to the right-hand side the transformed equation. Table 8 gathers the expressions of the resulting differential equations, needed for the implementation of PDE-LDDMM methods in SL form. For SL-RK, the right-hand side expressions can be directly plugged into an RK differential solver. Algorithm A1 shows the pseudocode for SL-RK integration.
Rights and permissions
About this article
Cite this article
Hernandez, M. Combining the Band-Limited Parameterization and Semi-Lagrangian Runge–Kutta Integration for Efficient PDE-Constrained LDDMM. J Math Imaging Vis 63, 555–579 (2021). https://doi.org/10.1007/s10851-021-01016-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10851-021-01016-4