A dynamic reconstruction and motion estimation framework for cardiorespiratory motion-resolved real-time volumetric MR imaging (DREME-MR) Journal Article
| Authors: | Shao, H. C.; Qian, X.; Xu, G.; Wu, C.; Otazo, R.; Deng, J.; Zhang, Y. |
| Article Title: | A dynamic reconstruction and motion estimation framework for cardiorespiratory motion-resolved real-time volumetric MR imaging (DREME-MR) |
| Abstract: | Objective. Based on a three-dimensional (3D) pre-treatment magnetic resonance (MR) scan, we developed a dynamic reconstruction and motion estimation technique for MR (DREME-MR) to jointly reconstruct a reference patient anatomy and solve a data-driven, patient-specific cardiorespiratory motion model. Via a motion encoder simultaneously learned during the reconstruction, DREME-MR further enables real-time volumetric MR imaging and cardiorespiratory motion tracking with minimal intra-treatment k-space data. Approach. DREME-MR integrates dynamic MRI reconstruction and real-time MR imaging into a unified, dual-task learning framework. From a 3D radial-spoke-based pre-treatment MR scan, DREME-MR uses spatiotemporal implicit-neural-representation (INR) to reconstruct pre-treatment dynamic volumetric MR images (learning task 1). The INR-based reconstruction takes a joint image reconstruction and deformable registration approach, yielding a reference anatomy and a corresponding cardiorespiratory motion model. The motion model adopts a low-rank, multi-resolution representation to approximate motion fields as products of motion coefficients and motion basis components (MBCs). Via a progressive, frequency-guided strategy, DREME-MR decouples cardiac MBCs from respiratory MBCs to resolve the two distinct motion modes. Simultaneously with the pre-treatment dynamic MRI reconstruction, DREME-MR also trains a multilayer perceptron-based motion encoder to infer cardiorespiratory motion coefficients directly from the raw k-space data (learning task 2), allowing real-time, intra-treatment volumetric MR imaging and motion tracking with minimal k-space data (20-30 spokes) acquired after the pre-treatment MRI scan. Main results. Evaluated using data from a digital phantom extended cardiac torso (XCAT) and a human scan, DREME-MR solves real-time 3D cardiorespiratory motion with a latency of <165 ms (=150 ms data acquisition + 15 ms inference time), fulfilling the temporal constraint of real-time imaging. The XCAT study achieves mean (±S.D.) center-of-mass tracking errors of 0.73 ± 0.38 mm for a lung tumor and 1.69 ± 1.12 mm for the left ventricle (LV). The human study shows good motion correlations (liver: 0.96; LV 0.65) between DREME-MR-solved motion and extracted surrogate signals. Significance. DREME-MR allows real-time 3D MRI and cardiorespiratory motion tracking with a low latency, advancing intra-treatment MR-guided adaptive radiotherapy, including real-time multileaf collimator tracking. © 2025 Elsevier B.V., All rights reserved. |
| Keywords: | magnetic resonance imaging; magnetic resonance; patient treatment; heart; image reconstruction; respiratory motions; motion estimation; respiratory mechanics; phantoms; three dimensional computer graphics; 3D reconstruction; respiratory motion; motion compensation; learning systems; dynamic mri; mr-guided radiotherapy; motion tracking; real-time motion; multilayers; cardiac motion; dynamic mri reconstruction; real-time motion tracking; dynamic reconstruction; magnetic resonance-guided radiotherapy; mri reconstruction |
| Journal Title: | Physics in Medicine and Biology |
| Volume: | 70 |
| Issue: | 17 |
| ISSN: | 00319155 |
| Publisher: | Elsevier B.V. |
| Date Published: | 2025-01-01 |
| Start Page: | 175013 |
| Language: | English |
| DOI: | 10.1088/1361-6560/adf9b9 |
| PROVIDER: | scopus |
| PMCID: | PMC12379086 |
| PUBMED: | 40780250 |
| DOI/URL: | |
| Notes: | Article -- Source: Scopus |
Altmetric
Citation Impact
BMJ Impact Analytics
Related MSK Work