An anatomically-informed correspondence initialisation method to improve learning-based registration for radiotherapy

TL;DR

This paper introduces an anatomically-informed initialisation technique for CT non-rigid registration that enhances learning-based methods' accuracy and speed by leveraging organ structure correspondences and a TPS deformation.

Contribution

It presents a novel initialisation approach using learned organ correspondences and TPS deformation to improve registration accuracy and efficiency in radiotherapy planning.

Findings

Improved registration accuracy with reduced distance-to-agreement.

Enhanced performance of learning-based registration to match traditional methods.

Significant speed advantage over iterative algorithms.

Abstract

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).