Saved in:
Bibliographic Details
Main Authors: Xie, Jiacheng, Shao, Hua-Chieh, Wu, Can, Otazo, Ricardo, Deng, Jie, Lin, Mu-Han, Chiu, Tsuicheng, Buatti, Jacob, Iakovenko, Viktor, Zhang, You
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.06482
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908945903255552
author Xie, Jiacheng
Shao, Hua-Chieh
Wu, Can
Otazo, Ricardo
Deng, Jie
Lin, Mu-Han
Chiu, Tsuicheng
Buatti, Jacob
Iakovenko, Viktor
Zhang, You
author_facet Xie, Jiacheng
Shao, Hua-Chieh
Wu, Can
Otazo, Ricardo
Deng, Jie
Lin, Mu-Han
Chiu, Tsuicheng
Buatti, Jacob
Iakovenko, Viktor
Zhang, You
contents Time-resolved volumetric MR imaging that reconstructs a 3D MRI within sub-seconds to resolve deformable motion is essential for motion-adaptive radiotherapy. Representing patient anatomy and associated motion fields as 3D Gaussians, we developed a spatiotemporal Gaussian representation-based framework (DREME-GSMR), which enables time-resolved dynamic MRI reconstruction from a pre-treatment 3D MR scan without any prior anatomical/motion model. DREME-GSMR represents a reference MRI volume and a corresponding low-rank motion model (as motion-basis components) using 3D Gaussians, and incorporates a dual-path MLP/CNN motion encoder to estimate temporal motion coefficients of the motion model from raw k-space-derived signals. Furthermore, using the solved motion model, DREME-GSMR can infer motion coefficients directly from new online k-space data, allowing subsequent intra-treatment volumetric MR imaging and motion tracking (real-time imaging). A motion-augmentation strategy is further introduced to improve robustness to unseen motion patterns during real-time imaging. DREME-GSMR was evaluated on the XCAT digital phantom, a physical motion phantom, and MR-LINAC datasets acquired from 6 healthy volunteers and 20 patients (with independent sequential scans for cross-evaluation). DREME-GSMR reconstructs MRIs of a ~400ms temporal resolution, with an inference time of ~10ms/volume. In XCAT experiments, DREME-GSMR achieved mean(s.d.) SSIM, tumor center-of-mass-error(COME), and DSC of 0.92(0.01)/0.91(0.02), 0.50(0.15)/0.65(0.19) mm, and 0.92(0.02)/0.92(0.03) for dynamic reconstruction/real-time imaging. For the physical phantom, the mean target COME was 1.19(0.94)/1.40(1.15) mm for dynamic/real-time imaging, while for volunteers and patients, the mean liver COME for real-time imaging was 1.31(0.82) and 0.96(0.64) mm, respectively.
format Preprint
id arxiv_https___arxiv_org_abs_2604_06482
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Spatiotemporal Gaussian representation-based dynamic reconstruction and motion estimation framework for time-resolved volumetric MR imaging (DREME-GSMR)
Xie, Jiacheng
Shao, Hua-Chieh
Wu, Can
Otazo, Ricardo
Deng, Jie
Lin, Mu-Han
Chiu, Tsuicheng
Buatti, Jacob
Iakovenko, Viktor
Zhang, You
Medical Physics
Machine Learning
Time-resolved volumetric MR imaging that reconstructs a 3D MRI within sub-seconds to resolve deformable motion is essential for motion-adaptive radiotherapy. Representing patient anatomy and associated motion fields as 3D Gaussians, we developed a spatiotemporal Gaussian representation-based framework (DREME-GSMR), which enables time-resolved dynamic MRI reconstruction from a pre-treatment 3D MR scan without any prior anatomical/motion model. DREME-GSMR represents a reference MRI volume and a corresponding low-rank motion model (as motion-basis components) using 3D Gaussians, and incorporates a dual-path MLP/CNN motion encoder to estimate temporal motion coefficients of the motion model from raw k-space-derived signals. Furthermore, using the solved motion model, DREME-GSMR can infer motion coefficients directly from new online k-space data, allowing subsequent intra-treatment volumetric MR imaging and motion tracking (real-time imaging). A motion-augmentation strategy is further introduced to improve robustness to unseen motion patterns during real-time imaging. DREME-GSMR was evaluated on the XCAT digital phantom, a physical motion phantom, and MR-LINAC datasets acquired from 6 healthy volunteers and 20 patients (with independent sequential scans for cross-evaluation). DREME-GSMR reconstructs MRIs of a ~400ms temporal resolution, with an inference time of ~10ms/volume. In XCAT experiments, DREME-GSMR achieved mean(s.d.) SSIM, tumor center-of-mass-error(COME), and DSC of 0.92(0.01)/0.91(0.02), 0.50(0.15)/0.65(0.19) mm, and 0.92(0.02)/0.92(0.03) for dynamic reconstruction/real-time imaging. For the physical phantom, the mean target COME was 1.19(0.94)/1.40(1.15) mm for dynamic/real-time imaging, while for volunteers and patients, the mean liver COME for real-time imaging was 1.31(0.82) and 0.96(0.64) mm, respectively.
title Spatiotemporal Gaussian representation-based dynamic reconstruction and motion estimation framework for time-resolved volumetric MR imaging (DREME-GSMR)
topic Medical Physics
Machine Learning
url https://arxiv.org/abs/2604.06482