Review of large deformation diffeomorphic metric mapping registration

Xiuhua Huang; Suhaila Abd Halim; Normi Abdul Hadi.

Transactions on Science and Technology, 12(4), Article ID ToST124RA1, pp 1 - 11.

Back to main issue

ABSTRACT
This study investigates the development and clinical applications of Large Deformation Diffeomorphic Metric Mapping (LDDMM) in medical image registration. Through systematic comparison between conventional optimization-based methods and contemporary deep learning techniques, we evaluate their respective performance in registration accuracy, computational efficiency, and clinical utility. Our methodology encompasses a thorough examination of both mathematical foundations and neural network implementations in LDDMM. Results demonstrate that traditional approaches maintain superior precision for complex anatomical variations via rigorous variational optimization, whereas deep learning methods achieve substantial computational acceleration (reducing processing time from hours to seconds) through learned deformation patterns. Critical analysis reveals important trade-offs: while deep learning offers remarkable speed improvements, traditional methods preserve accuracy advantages in specialized clinical scenarios. We identify key challenges including computational complexity, implementation difficulties, and domain adaptation limitations, while proposing hybrid architecture and transfer learning as potential solutions. The study concludes that integrating the mathematical robustness of conventional LDDMM with the computational efficiency of deep learning presents the most viable path forward. Such synergistic approaches promise to advance medical image analysis pipelines and promote wider clinical implementation of sophisticated registration technologies.

KEYWORDS: : LDDMM; Image registration; Deep learning



Download this PDF file

REFERENCES
  1. Amor, B. B., Arguillère, S. & Shao, L. 2022. ResNet-LDDMM: advancing the LDDMM framework using deep residual networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(3), 3707-3720.
  2. Balakrishnan, G., Zhao, A., Sabuncu, M. R., Guttag, J. & Dalca, A. V. 2019. Voxelmorph: A Learning Framework for Deformable Medical Image Registration. IEEE Transactions on Medical Imaging, 38(8), 1788-1800.
  3. Beg, M. F., Miller, M. I., Trouvé, A. & Younes, L. 2005. Computing large deformation metric mappings via geodesic flows of diffeomorphisms. International Journal of Computer Vision, 61(2), 139-157.
  4. Cao, Y., Miller, M. I., Mori, S., Winslow, R. L. & Younes, L. 2006. Diffeomorphic Matching of Diffusion Tensor Images. Proceedings of the 2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'06). 17-22 June, New York, USA. pp 67-67.
  5. Cao, Y., Miller, M. I., Winslow, R. L. & Younes, L. 2005. Large Deformation Diffeomorphic Metric Mapping of Vector Fields. IEEE Transactions on Medical Imaging, 24(9), 1216-1230.
  6. Charon, N. & Trouvé, A. 2013. The Varifold Representation of Nonoriented Shapes for Diffeomorphic Registration. SIAM journal on Imaging Sciences, 6(4), 2547-2580.
  7. Chen, X., Diaz-Pinto, A., Ravikumar, N. & Frangi, A. F. 2021. Deep learning in medical image registration. Progress in Biomedical Engineering, 3(1), 012003.
  8. Ding, Z., Fleishman, G., Yang, X., Thompson, PKwitt, R., Niethammer, M. & Alzheimer’s Disease Neuroimaging Initiative. 2019. Fast Predictive Simple Geodesic Regression. Medical Image Analysis, 56, 193-209.
  9. Glaunes, J., Qiu, A., Miller, M. I. & Younes, L. 2008. Large Deformation Diffeomorphic Metric Curve Mapping. International Journal of Computer Vision, 80, 317-336.
  10. Goshtasby, A. A. 2012. Image Registration: Principles, Tools and Methods. Londin: Springer.
  11. Grenander, U. 1994. General Pattern Theory: A Mathematical Study of Regular Structures. Oxford University Press.
  12. Grenander, U. & Miller, M. I. 1998. Computational Anatomy: An Emerging Discipline. Quarterly of Applied Mathematics, 56(4), 617-694.
  13. Griewank, A. 1992. Achieving Logarithmic Growth of Temporal and Spatial Complexity in Reverse Automatic Differentiation. Optimization Methods and Software, 1(1), 35-54.
  14. Guan, D., Tian, L., Li, W. & Gao, H. 2024. Using LDDMM and a Kinematic Cardiac Growth Model to Quantify Growth and Remodelling in Rat Hearts Under PAH. Computers in Biology and Medicine, 108218.
  15. Guan, S., Wang, T., Sun, K. & Meng, C. 2020a. Transfer Learning for Nonrigid 2D/3D Cardiovascular Images Registration. IEEE Journal of Biomedical and Health Informatics, 25(9), 3300-3309.
  16. Guan, D., Yao, J., Luo, X. & Gao, H. 2020b. Effect of Myofibre Architecture on Ventricular Pump Function by using A Neonatal Porcine Heart Model: from DT-MRI to Rule-Based Methods. Royal Society Open Science, 7(4), 191655.
  17. Hernandez, M. 2017. Primal-dual Convex Optimization in Large Deformation Diffeomorphic Metric Mapping: LDDMM Meets Robust Regularizers. Physics in Medicine & Biology, 62(23), 9067.
  18. Hernandez, M. 2018. Newton-Krylov PDE-constrained LDDMM in the Space of Band-Limited Vector Fields. https://doi.org/10.48550/arXiv.1807.05117.
  19. Hernandez, M. 2019. PDE-constrained LDDMM via Geodesic Shooting and Inexact Gauss–Newton–Krylov Optimization using the Incremental Adjoint Jacobi Equations. Physics in Medicine & Biology, 64(2), 025002.
  20. Hernandez, M. 2021a. Combining the Band-Limited Parameterization and Semi-Lagrangian Runge–Kutta Integration for Efficient PDE-Constrained LDDMM. Journal of Mathematical Imaging and Vision, 63(5), 555-579.
  21. Hernandez, M. 2021b. Efficient momentum conservation constrained PDE-LDDMM with Gauss–Newton–Krylov Optimization, Semi-Lagrangian Runge–Kutta Solvers, and the Band-limited Parameterization. Journal of Computational Science, 55, 101470.
  22. Hernandez, M. 2025. PDE-LDDMM Meets Nodes: Introducing Neural Ordinary Differential Equation Solvers in PDE-constrained Large Deformation Diffeomorphic Metric Mapping. Journal of Computational Science, 85, 102507.
  23. Hernandez, M., Ramon-Julvez, U. & Sierra-Tome, D. 2022. Partial Differential Equation-Constrained Diffeomorphic Registration from Sum of Squared Differences to Normalized Cross-Correlation, Normalized Gradient Fields, and Mutual Information: A Unifying Framework. Sensors, 22(10), 3735.
  24. Hsieh, H. W. & Charon, N. 2022. Weight metamorphosis of varifolds and the LDDMM-Fisher-Rao metric. Calculus of Variations and Partial Differential Equations, 61(5), 165.
  25. Hsieh, H. W. & Charon, N. 2021. Metrics, Quantization and Registration in Varifold Spaces. Foundations of Computational Mathematics, 21(5), 1317-1361.
  26. Joshi, S., Davis, B., Jomier, M. & Gerig, G. 2004. Unbiased Diffeomorphic Atlas Construction for Computational Anatomy. NeuroImage, 23(1), S151-S160.
  27. Joshi, S. C. & Miller, M. I. 2000. Landmark Matching Via Large Deformation Diffeomorphisms. IEEE Transactions on Image Processing, 9(8), 1357-1370.
  28. Mang, A., He, J. & Azencott, R. 2023. An Operator-Splitting Approach for Variational Optimal Control Formulations for Diffeomorphic Shape Matching. Journal of Computational Physics, 493, 112463.
  29. Polzin, T., Niethammer, M., Heinrich, M. P., Handels, H. & Modersitzki, J. 2016. Memory efficient LDDMM for lung CT. Proceedings of the 19th International Conference of Medical Image Computing and Computer-Assisted Intervention-MICCAI 2016. 17-21 October, 2016, Athens, Greece. pp 28-36.
  30. Polzin, T., Niethammer, M., Vialard, F. X. & Modersitzki, J. 2020. A Discretize–Optimize Approach for LDDMM Registration. Riemannian Geometric Statistics in Medical Image Analysis. 479-532.
  31. Polzin, T. 2018. Large Deformation Diffeomorphic Metric Mappings: Theory, Numerics, and Applications. Doctoral Thesis, University of Lübeck, Germany.
  32. Ramon, U., Hernandez, M. & Mayordomo, E. 2022. LDDMM meets GANs: Generative Adversarial Networks for diffeomorphic registration. In: Hering, A., Schnabel, J., Zhang, M., Ferrante, E., Heinrich, M., Rueckert, D. (eds). Biomedical Image Registration. WBIR 2022. Lecture Notes in Computer Science, vol 13386. Cham: Springer. pp. 18-28.
  33. Richardson, C. L. & Younes, L. 2016. Metamorphosis of Images in Reproducing Kernel Hilbert Spaces. Advances in Computational Mathematics, 42, 573-603.
  34. Sakamoto, R., Mori, S., Miller, M. I., Okada, T. & Togashi, K. 2014. Detection of Time-Varying Structures by Large Deformation Diffeomorphic Metric Mapping to Aid Reading of High-Resolution CT Images Of The Lung. PLoS One, 9(1), e85580.
  35. Singh, N., Hinkle, J., Joshi, S. & Fletcher, P. T. 2013, April. A Vector Momenta Formulation of Diffeomorphisms for Improved Geodesic Regression and Atlas Construction. Proceedings of the 2013 IEEE 10th International Symposium on Biomedical Imaging. 7-11 April, 2013, San Francisco, California, USA. pp 1219-1222.
  36. Stouffer, K. M., Witter, M. P., Tward, D. J. & Miller, M. I. 2022. Projective LDDMM: Mapping Molecular Digital Pathology with Tissue MRI. bioRxiv, 2022-04.
  37. Vaillant, M., Qiu, A., Glaunès, J. & Miller, M. I. 2007. Diffeomorphic Metric Surface Mapping in Subregion of the Superior Temporal Gyrus. NeuroImage, 34(3), 1149-1159.
  38. 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.
  39. Wang, J. & Zhang, M. 2020a. Deepflash: An Efficient Network for Learning-Based Medical Image Registration. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 13-19 June, 2020, Seattle, WA, USA. pp 4444-4452.
  40. Wang, J. & Zhang, M. 2020b. Deep Learning for Regularization Prediction in Diffeomorphic Image Registration (https://doi.org/10.48550/arXiv.2011.14229). Last accessed on 22 October 2025.
  41. Wu, J. & Gong, K. 2025. Unsupervised Learning-Based Large Deformation Diffeomorphic Metric Mapping for Fast Image Registration. Proceedings of the 2025 IEEE 22nd International Symposium on Biomedical Imaging (ISBI). 14-17 April, 2025, London, UK. pp 1-5.
  42. Wu, J. & Tang, X. 2020. A Large Deformation Diffeomorphic Framework for Fast Brain Image Registration Via Parallel Computing and Optimization. Neuroinformatics, 18(2), 251-266.
  43. Wu, J., Zhou, S., Yang, Q., Zhang, Y. & Tang, X. 2021, November. Multi-modality Large Deformation Diffeomorphic Metric Mapping Driven by Single-modality Images. Proceedings of the 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). 1-5 November, 2021, Guadalajara, Mexico. pp. 2610-2613.
  44. Yang, H., Lyu, J., Tam, R. & Tang, X. 2023. A Survey on Deep Learning-Based Diffeomorphic Mapping. In: Chen, K., Schonlieb, C. B., Tai, X. C. & Younes, L. (Eds.). Handbook of Mathematical Models and Algorithms in Computer Vision and Imaging: Mathematical Imaging and Vision. Cham: Springe.
  45. Yang, H., Lyu, J., Cheng, P., Tam, R. & Tang, X. 2024. LDDMM-Face: Large deformation diffeomorphic metric learning for cross-annotation face alignment. Pattern Recognition, 154, 110569.
  46. Yang, H., Wang, J., Tang, H., Ba, Q., Yang, G. & Tang, X. 2017a. Analysis of Mitochondrial Shape Dynamics using Large Deformation Diffeomorphic Metric Curve Matching. Proceedings of the 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). 11-15 July, 2017, Jeju Island, South Korea. pp 4062-4065.
  47. Yang, X., Kwitt, R. & Niethammer, M. 2016. Fast Predictive Image Registration. In: Carneiro, G., Mateus, D., Peter, L., Bradley, A., Tavares, J. M. R. S., Belagiannis, V., Papa, J. P., Nascimento, J. C., Loog, M., Lu, Z., Cardoso, J. S. & Cornebise, J. (Eds.). Deep Learning and Data Labeling for Medical Applications (Vol. 10008). Cham: Springer.
  48. Yang, X., Kwitt, R., Styner, M. & Niethammer, M. 2017b. Quicksilver: Fast Predictive Image Registration–A Deep Learning Approach. NeuroImage, 158, 378-396.
  49. Ye, M., Yang, D., Kanski, M., Axel, L. & Metaxas, D. 2023. Neural Deformable Models for 3D Bi-Ventricular Heart Shape Reconstruction and Modeling from 2D Sparse Cardiac Magnetic Resonance Imaging. Proceedings of the IEEE/CVF International Conference on Computer Vision. 1-6 October, 2023, Paris, France. pp 14247-14256.
  50. Younes, L. 2019. Deformable Objects and Matching Functionals. In: Bloch, A., Epstein, C. L., Goriely, A., Greengard, L. & Holmes, P. J. (Eds.). Shapes and Diffeomorphisms (Vol. 171). Berlin: Springer.
  51. Zhang, H., Ni, W., Yan, W., Xiang, D., Wu, J., Yang, X. & Bian, H. 2019. Registration of Multimodal Remote Sensing Image Based on Deep Fully Convolutional Neural Network. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 12(8), 3028-3042.