TY - GEN
T1 - Learning-based Image Registration with Meta-Regularization
AU - Al Safadi, Ebrahim
AU - Song, Xubo
N1 - Publisher Copyright:
© 2021 IEEE
PY - 2021
Y1 - 2021
N2 - We introduce a meta-regularization framework for learning-based image registration. Current learning-based image registration methods use high-resolution architectures such as U-Nets to produce spatial transformations, and impose simple and explicit regularization on the output of the network to ensure that the estimated displacements are smooth. While this approach works well on small deformations, it has been known to struggle when the deformations are large. Our method uses a more advanced form of meta-regularization to increase the generalization ability of learned registration models. We motivate our approach based on Reproducing Kernel Hilbert Space (RKHS) theory, and approximate that framework via a meta-regularization convolutional layer with radially symmetric, positive semi-definite filters that inherent its regularization properties. We then provide a method to learn such regularization filters while also learning to register. Our experiments on synthetic and real datasets as well as ablation analysis show that our method can improve anatomical correspondence compared to competing methods, and reduce the percentage of folding and tear in the large deformation setting, reflecting better regularization and model generalization.
AB - We introduce a meta-regularization framework for learning-based image registration. Current learning-based image registration methods use high-resolution architectures such as U-Nets to produce spatial transformations, and impose simple and explicit regularization on the output of the network to ensure that the estimated displacements are smooth. While this approach works well on small deformations, it has been known to struggle when the deformations are large. Our method uses a more advanced form of meta-regularization to increase the generalization ability of learned registration models. We motivate our approach based on Reproducing Kernel Hilbert Space (RKHS) theory, and approximate that framework via a meta-regularization convolutional layer with radially symmetric, positive semi-definite filters that inherent its regularization properties. We then provide a method to learn such regularization filters while also learning to register. Our experiments on synthetic and real datasets as well as ablation analysis show that our method can improve anatomical correspondence compared to competing methods, and reduce the percentage of folding and tear in the large deformation setting, reflecting better regularization and model generalization.
UR - http://www.scopus.com/inward/record.url?scp=85121195050&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85121195050&partnerID=8YFLogxK
U2 - 10.1109/CVPR46437.2021.01078
DO - 10.1109/CVPR46437.2021.01078
M3 - Conference contribution
AN - SCOPUS:85121195050
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 10923
EP - 10932
BT - Proceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021
PB - IEEE Computer Society
T2 - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021
Y2 - 19 June 2021 through 25 June 2021
ER -