Saved in:
Bibliographic Details
Main Authors: Henderson, Edward G. A., van Herk, Marcel, Green, Andrew F., Osorio, Eliana M. Vasquez
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.19101
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913707735384064
author Henderson, Edward G. A.
van Herk, Marcel
Green, Andrew F.
Osorio, Eliana M. Vasquez
author_facet Henderson, Edward G. A.
van Herk, Marcel
Green, Andrew F.
Osorio, Eliana M. Vasquez
contents We propose an anatomically-informed initialisation method for interpatient CT non-rigid registration (NRR), using a learning-based model to estimate correspondences between organ structures. A thin plate spline (TPS) deformation, set up using the correspondence predictions, is used to initialise the scans before a second NRR step. We compare two established NRR methods for the second step: a B-spline iterative optimisation-based algorithm and a deep learning-based approach. Registration performance is evaluated with and without the initialisation by assessing the similarity of propagated structures. Our proposed initialisation improved the registration performance of the learning-based method to more closely match the traditional iterative algorithm, with the mean distance-to-agreement reduced by 1.8mm for structures included in the TPS and 0.6mm for structures not included, while maintaining a substantial speed advantage (5 vs. 72 seconds).
format Preprint
id arxiv_https___arxiv_org_abs_2502_19101
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle An anatomically-informed correspondence initialisation method to improve learning-based registration for radiotherapy
Henderson, Edward G. A.
van Herk, Marcel
Green, Andrew F.
Osorio, Eliana M. Vasquez
Computer Vision and Pattern Recognition
We propose an anatomically-informed initialisation method for interpatient CT non-rigid registration (NRR), using a learning-based model to estimate correspondences between organ structures. A thin plate spline (TPS) deformation, set up using the correspondence predictions, is used to initialise the scans before a second NRR step. We compare two established NRR methods for the second step: a B-spline iterative optimisation-based algorithm and a deep learning-based approach. Registration performance is evaluated with and without the initialisation by assessing the similarity of propagated structures. Our proposed initialisation improved the registration performance of the learning-based method to more closely match the traditional iterative algorithm, with the mean distance-to-agreement reduced by 1.8mm for structures included in the TPS and 0.6mm for structures not included, while maintaining a substantial speed advantage (5 vs. 72 seconds).
title An anatomically-informed correspondence initialisation method to improve learning-based registration for radiotherapy
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2502.19101