SINR: Spline-enhanced implicit neural representation for multi-modal registration

Vasiliki Sideri-Lampretsa, Julian McGinnis, Huaqi Qiu, Magdalini Paschali, Walter Simson, Daniel Rueckert
Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning, PMLR 250:1462-1474, 2024.

Abstract

Deformable image registration has undergone a transformative shift with the advent of deep learning. While convolutional neural networks (CNNs) allow for accelerated registration, they exhibit reduced accuracy compared to iterative pairwise optimization methods and require extensive training cohorts. Based on the advances in representing signals with neural networks, implicit neural representations (INRs) have emerged in the registration community to model dense displacement fields continuously. Using a pairwise registration setup, INRs mitigate the bias learned over a cohort of patients while leveraging advanced methodology and gradient-based optimization. However, the coordinate sampling scheme makes dense transformation parametrization with an INR prone to generating physiologically implausible configurations resulting in spatial folding. In this paper, we introduce SINR - a method to parameterize the continuous deformable transformation represented by an INR using Free Form Deformations (FFD). SINR allows for multi-modal deformable registration while mitigating folding issues found in current INR-based registration methods. SINR outperforms existing state-of-the-art methods on both 3D mono- and multi-modal brain registration on the CamCAN dataset, demonstrating its capabilities for pairwise mono- and multi-modal image registration.

Cite this Paper

BibTeX
@InProceedings{pmlr-v250-sideri-lampretsa24a, title = {SINR: Spline-enhanced implicit neural representation for multi-modal registration}, author = {Sideri-Lampretsa, Vasiliki and McGinnis, Julian and Qiu, Huaqi and Paschali, Magdalini and Simson, Walter and Rueckert, Daniel}, booktitle = {Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning}, pages = {1462--1474}, year = {2024}, editor = {Burgos, Ninon and Petitjean, Caroline and Vakalopoulou, Maria and Christodoulidis, Stergios and Coupe, Pierrick and Delingette, Hervé and Lartizien, Carole and Mateus, Diana}, volume = {250}, series = {Proceedings of Machine Learning Research}, month = {03--05 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v250/main/assets/sideri-lampretsa24a/sideri-lampretsa24a.pdf}, url = {https://proceedings.mlr.press/v250/sideri-lampretsa24a.html}, abstract = {Deformable image registration has undergone a transformative shift with the advent of deep learning. While convolutional neural networks (CNNs) allow for accelerated registration, they exhibit reduced accuracy compared to iterative pairwise optimization methods and require extensive training cohorts. Based on the advances in representing signals with neural networks, implicit neural representations (INRs) have emerged in the registration community to model dense displacement fields continuously. Using a pairwise registration setup, INRs mitigate the bias learned over a cohort of patients while leveraging advanced methodology and gradient-based optimization. However, the coordinate sampling scheme makes dense transformation parametrization with an INR prone to generating physiologically implausible configurations resulting in spatial folding. In this paper, we introduce SINR - a method to parameterize the continuous deformable transformation represented by an INR using Free Form Deformations (FFD). SINR allows for multi-modal deformable registration while mitigating folding issues found in current INR-based registration methods. SINR outperforms existing state-of-the-art methods on both 3D mono- and multi-modal brain registration on the CamCAN dataset, demonstrating its capabilities for pairwise mono- and multi-modal image registration.} }
Endnote
%0 Conference Paper %T SINR: Spline-enhanced implicit neural representation for multi-modal registration %A Vasiliki Sideri-Lampretsa %A Julian McGinnis %A Huaqi Qiu %A Magdalini Paschali %A Walter Simson %A Daniel Rueckert %B Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2024 %E Ninon Burgos %E Caroline Petitjean %E Maria Vakalopoulou %E Stergios Christodoulidis %E Pierrick Coupe %E Hervé Delingette %E Carole Lartizien %E Diana Mateus %F pmlr-v250-sideri-lampretsa24a %I PMLR %P 1462--1474 %U https://proceedings.mlr.press/v250/sideri-lampretsa24a.html %V 250 %X Deformable image registration has undergone a transformative shift with the advent of deep learning. While convolutional neural networks (CNNs) allow for accelerated registration, they exhibit reduced accuracy compared to iterative pairwise optimization methods and require extensive training cohorts. Based on the advances in representing signals with neural networks, implicit neural representations (INRs) have emerged in the registration community to model dense displacement fields continuously. Using a pairwise registration setup, INRs mitigate the bias learned over a cohort of patients while leveraging advanced methodology and gradient-based optimization. However, the coordinate sampling scheme makes dense transformation parametrization with an INR prone to generating physiologically implausible configurations resulting in spatial folding. In this paper, we introduce SINR - a method to parameterize the continuous deformable transformation represented by an INR using Free Form Deformations (FFD). SINR allows for multi-modal deformable registration while mitigating folding issues found in current INR-based registration methods. SINR outperforms existing state-of-the-art methods on both 3D mono- and multi-modal brain registration on the CamCAN dataset, demonstrating its capabilities for pairwise mono- and multi-modal image registration.
APA
Sideri-Lampretsa, V., McGinnis, J., Qiu, H., Paschali, M., Simson, W. & Rueckert, D.. (2024). SINR: Spline-enhanced implicit neural representation for multi-modal registration. Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 250:1462-1474 Available from https://proceedings.mlr.press/v250/sideri-lampretsa24a.html.

Related Material