Real-time MR-based 3D motion monitoring using raw k-space data

Marius Krusen, Floris Ernst
Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning, PMLR 250:768-781, 2024.

Abstract

Due to its great soft-tissue contrast and non-invasive nature, magnetic resonance imaging (MRI) is uniquely qualified for motion monitoring during radiotherapy.However, real-time capabilities are limited by its long acquisition times, particularly in 3D, and require highly undersampling k-space resulting in lower image resolution and image artifacts.In this paper, we propose a simple recurrent neural network (RNN) architecture to continually estimate target motion from single k-space spokes.By directly using the incoming k-space data, additional image reconstruction steps are avoided and less data is required between estimations achieving a latency of only a few milliseconds.The 4D XCAT phantom was used to generate realistic data of the abdomen affected by respiratory and cardiac motion and a simulated lesion inserted into the liver acted as the target.We show that using a Kooshball trajectory to sample 3D k-space gives superior results compared to a stack-of-stars (SoS) trajectory.The RNN quickly learns the motion pattern and can give new motion estimations at a frequency of more than 230 Hz, demonstrating the feasibility of drastically improving latency of MR-based motion monitoring systems.

Cite this Paper


BibTeX
@InProceedings{pmlr-v250-krusen24a, title = {Real-time MR-based 3D motion monitoring using raw k-space data}, author = {Krusen, Marius and Ernst, Floris}, booktitle = {Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning}, pages = {768--781}, 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/krusen24a/krusen24a.pdf}, url = {https://proceedings.mlr.press/v250/krusen24a.html}, abstract = {Due to its great soft-tissue contrast and non-invasive nature, magnetic resonance imaging (MRI) is uniquely qualified for motion monitoring during radiotherapy.However, real-time capabilities are limited by its long acquisition times, particularly in 3D, and require highly undersampling k-space resulting in lower image resolution and image artifacts.In this paper, we propose a simple recurrent neural network (RNN) architecture to continually estimate target motion from single k-space spokes.By directly using the incoming k-space data, additional image reconstruction steps are avoided and less data is required between estimations achieving a latency of only a few milliseconds.The 4D XCAT phantom was used to generate realistic data of the abdomen affected by respiratory and cardiac motion and a simulated lesion inserted into the liver acted as the target.We show that using a Kooshball trajectory to sample 3D k-space gives superior results compared to a stack-of-stars (SoS) trajectory.The RNN quickly learns the motion pattern and can give new motion estimations at a frequency of more than 230 Hz, demonstrating the feasibility of drastically improving latency of MR-based motion monitoring systems.} }
Endnote
%0 Conference Paper %T Real-time MR-based 3D motion monitoring using raw k-space data %A Marius Krusen %A Floris Ernst %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-krusen24a %I PMLR %P 768--781 %U https://proceedings.mlr.press/v250/krusen24a.html %V 250 %X Due to its great soft-tissue contrast and non-invasive nature, magnetic resonance imaging (MRI) is uniquely qualified for motion monitoring during radiotherapy.However, real-time capabilities are limited by its long acquisition times, particularly in 3D, and require highly undersampling k-space resulting in lower image resolution and image artifacts.In this paper, we propose a simple recurrent neural network (RNN) architecture to continually estimate target motion from single k-space spokes.By directly using the incoming k-space data, additional image reconstruction steps are avoided and less data is required between estimations achieving a latency of only a few milliseconds.The 4D XCAT phantom was used to generate realistic data of the abdomen affected by respiratory and cardiac motion and a simulated lesion inserted into the liver acted as the target.We show that using a Kooshball trajectory to sample 3D k-space gives superior results compared to a stack-of-stars (SoS) trajectory.The RNN quickly learns the motion pattern and can give new motion estimations at a frequency of more than 230 Hz, demonstrating the feasibility of drastically improving latency of MR-based motion monitoring systems.
APA
Krusen, M. & Ernst, F.. (2024). Real-time MR-based 3D motion monitoring using raw k-space data. Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 250:768-781 Available from https://proceedings.mlr.press/v250/krusen24a.html.

Related Material