Multi-Objective Learning for Deformable Image Registration

Monika Grewal, Henrike Westerveld, Peter Bosman, Tanja Alderliesten
Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning, PMLR 250:538-553, 2024.

Abstract

Deformable image registration (DIR) involves optimization of multiple conflicting objectives, however, not many existing DIR algorithms are multi-objective (MO). Further, while there has been progress in the design of deep learning algorithms for DIR, there is no work in the direction of MO DIR using deep learning. In this paper, we fill this gap by combining a recently proposed approach for MO training of neural networks with a well-known deep neural network for DIR and create a deep learning based MO DIR approach. We evaluate the proposed approach for DIR of pelvic magnetic resonance imaging (MRI) scans. We experimentally demonstrate that the proposed MO DIR approach – providing multiple DIR outputs for each patient that each correspond to a different trade-off between the objectives – has additional desirable properties from a clinical use point-of-view as compared to providing a single DIR output. The experiments also show that the proposed MO DIR approach provides a better spread of DIR outputs across the entire trade-off front than simply training multiple neural networks with weights for each objective sampled from a grid of possible values.

Cite this Paper

BibTeX
@InProceedings{pmlr-v250-grewal24a, title = {Multi-Objective Learning for Deformable Image Registration}, author = {Grewal, Monika and Westerveld, Henrike and Bosman, Peter and Alderliesten, Tanja}, booktitle = {Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning}, pages = {538--553}, 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/grewal24a/grewal24a.pdf}, url = {https://proceedings.mlr.press/v250/grewal24a.html}, abstract = {Deformable image registration (DIR) involves optimization of multiple conflicting objectives, however, not many existing DIR algorithms are multi-objective (MO). Further, while there has been progress in the design of deep learning algorithms for DIR, there is no work in the direction of MO DIR using deep learning. In this paper, we fill this gap by combining a recently proposed approach for MO training of neural networks with a well-known deep neural network for DIR and create a deep learning based MO DIR approach. We evaluate the proposed approach for DIR of pelvic magnetic resonance imaging (MRI) scans. We experimentally demonstrate that the proposed MO DIR approach – providing multiple DIR outputs for each patient that each correspond to a different trade-off between the objectives – has additional desirable properties from a clinical use point-of-view as compared to providing a single DIR output. The experiments also show that the proposed MO DIR approach provides a better spread of DIR outputs across the entire trade-off front than simply training multiple neural networks with weights for each objective sampled from a grid of possible values.} }
Endnote
%0 Conference Paper %T Multi-Objective Learning for Deformable Image Registration %A Monika Grewal %A Henrike Westerveld %A Peter Bosman %A Tanja Alderliesten %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-grewal24a %I PMLR %P 538--553 %U https://proceedings.mlr.press/v250/grewal24a.html %V 250 %X Deformable image registration (DIR) involves optimization of multiple conflicting objectives, however, not many existing DIR algorithms are multi-objective (MO). Further, while there has been progress in the design of deep learning algorithms for DIR, there is no work in the direction of MO DIR using deep learning. In this paper, we fill this gap by combining a recently proposed approach for MO training of neural networks with a well-known deep neural network for DIR and create a deep learning based MO DIR approach. We evaluate the proposed approach for DIR of pelvic magnetic resonance imaging (MRI) scans. We experimentally demonstrate that the proposed MO DIR approach – providing multiple DIR outputs for each patient that each correspond to a different trade-off between the objectives – has additional desirable properties from a clinical use point-of-view as compared to providing a single DIR output. The experiments also show that the proposed MO DIR approach provides a better spread of DIR outputs across the entire trade-off front than simply training multiple neural networks with weights for each objective sampled from a grid of possible values.
APA
Grewal, M., Westerveld, H., Bosman, P. & Alderliesten, T.. (2024). Multi-Objective Learning for Deformable Image Registration. Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 250:538-553 Available from https://proceedings.mlr.press/v250/grewal24a.html.

Related Material