Papers
Topics
Authors
Recent
Search
2000 character limit reached

Fourier-Net: Fast Image Registration with Band-limited Deformation

Published 29 Nov 2022 in cs.CV | (2211.16342v2)

Abstract: Unsupervised image registration commonly adopts U-Net style networks to predict dense displacement fields in the full-resolution spatial domain. For high-resolution volumetric image data, this process is however resource-intensive and time-consuming. To tackle this problem, we propose the Fourier-Net, replacing the expansive path in a U-Net style network with a parameter-free model-driven decoder. Specifically, instead of our Fourier-Net learning to output a full-resolution displacement field in the spatial domain, we learn its low-dimensional representation in a band-limited Fourier domain. This representation is then decoded by our devised model-driven decoder (consisting of a zero padding layer and an inverse discrete Fourier transform layer) to the dense, full-resolution displacement field in the spatial domain. These changes allow our unsupervised Fourier-Net to contain fewer parameters and computational operations, resulting in faster inference speeds. Fourier-Net is then evaluated on two public 3D brain datasets against various state-of-the-art approaches. For example, when compared to a recent transformer-based method, named TransMorph, our Fourier-Net, which only uses 2.2\% of its parameters and 6.66\% of the multiply-add operations, achieves a 0.5\% higher Dice score and an 11.48 times faster inference speed. Code is available at \url{https://github.com/xi-jia/Fourier-Net}.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (36)
  1. Ashburner, J. 2007. A fast diffeomorphic image registration algorithm. Neuroimage, 38(1): 95–113.
  2. A reproducible evaluation of ANTs similarity metric performance in brain image registration. Neuroimage, 54(3): 2033–2044.
  3. VoxelMorph: A Learning Framework for Deformable Medical Image Registration. IEEE Transactions on Medical Imaging, 38(8): 1788–1800.
  4. Computing large deformation metric mappings via geodesic flows of diffeomorphisms. International journal of computer vision, 61(2): 139–157.
  5. TransMorph: Transformer for unsupervised medical image registration. arXiv preprint arXiv:2111.10480.
  6. ViT-V-Net: Vision Transformer for Unsupervised Volumetric Medical Image Registration. arXiv preprint arXiv:2104.06468.
  7. Unsupervised learning for fast probabilistic diffeomorphic registration. In International Conference on Medical Image Computing and Computer-Assisted Intervention, 729–738. Springer.
  8. A deep learning framework for unsupervised affine and deformable image registration. Medical image analysis, 52: 128–143.
  9. Automatic 3D bi-ventricular segmentation of cardiac images by a shape-refined multi-task deep learning approach. IEEE transactions on medical imaging, 38(9): 2151–2164.
  10. An edge-weighted second order variational model for image decomposition. Digital Signal Processing, 49: 162–181.
  11. Multi-modal Multi-Atlas Segmentation using Discrete Optimisation and Self-Similarities. VISCERAL Challenge@ ISBI, 1390: 27.
  12. Learn2Reg: comprehensive multi-task medical image registration challenge, dataset and evaluation in the era of deep learning. IEEE Transactions on Medical Imaging.
  13. Hernandez, M. 2018. Band-limited stokes large deformation diffeomorphic metric mapping. IEEE Journal of Biomedical and Health Informatics, 23(1): 362–373.
  14. Hypermorph: Amortized hyperparameter learning for image registration. In International Conference on Information Processing in Medical Imaging, 3–17. Springer.
  15. Spatial transformer networks. In Advances in Neural Information Processing Systems, 2017–2025.
  16. U-Net vs Transformer: Is U-Net Outdated in Medical Image Registration? arXiv preprint arXiv:2208.04939.
  17. Learning a Model-Driven Variational Network for Deformable Image Registration. IEEE Transactions on Medical Imaging, 41(1): 199–212.
  18. CycleMorph: cycle consistent unsupervised deformable image registration. Medical Image Analysis, 71: 102036.
  19. Unbiased longitudinal brain atlas creation using robust linear registration and log-Euclidean framework for diffeomorphisms. In 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), 1038–1041. IEEE.
  20. Implementation of high-order variational models made easy for image processing. Mathematical Methods in the Applied Sciences, 39(14): 4208–4233.
  21. An inexact Newton–Krylov algorithm for constrained diffeomorphic image registration. SIAM journal on imaging sciences, 8(2): 1030–1069.
  22. 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.
  23. Fast free-form deformation using graphics processing units. Computer methods and programs in biomedicine, 98(3): 278–284.
  24. Large deformation diffeomorphic image registration with laplacian pyramid networks. In International Conference on Medical Image Computing and Computer-Assisted Intervention, 211–221. Springer.
  25. Fast Symmetric Diffeomorphic Image Registration with Convolutional Neural Networks. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
  26. Learning Diffeomorphic and Modality-invariant Registration using B-splines. In Medical Imaging with Deep Learning.
  27. Nonrigid registration using free-form deformations: application to breast MR images. IEEE Transactions on Medical Imaging, 18(8): 712–721.
  28. Deformable medical image registration: A survey. IEEE Transactions on Medical Imaging, 32(7): 1153–1190.
  29. Nesterov Accelerated ADMM for Fast Diffeomorphic Image Registration. In International Conference on Medical Image Computing and Computer-Assisted Intervention, 150–160. Springer.
  30. Deep complex networks. arXiv preprint arXiv:1705.09792.
  31. Diffeomorphic demons: Efficient non-parametric image registration. NeuroImage, 45(1): S61–S72.
  32. DeepFlash: An efficient network for learning-based medical image registration. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 4444–4452.
  33. Quicksilver: Fast predictive image registration–a deep learning approach. NeuroImage, 158: 378–396.
  34. Zhang, J. 2018. Inverse-consistent deep networks for unsupervised deformable image registration. arXiv preprint arXiv:1809.03443.
  35. Fast diffeomorphic image registration via fourier-approximated lie algebras. International Journal of Computer Vision, 127(1): 61–73.
  36. Recursive Cascaded Networks for Unsupervised Medical Image Registration. In The IEEE International Conference on Computer Vision (ICCV).
Citations (20)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Sign Up to Summarize

Paper to Video (Beta)

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up