Shao Hua-Chieh, Qian Xiaoxue, Xu Guoping, Wu Can, Otazo Ricardo, Deng Jie, Zhang You
The Medical Artificial Intelligence and Automation (MAIA) Laboratory.
Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA.
ArXiv. 2025 Mar 26:arXiv:2503.21014v1.
Based on a 3D pre-treatment magnetic resonance (MR) scan, we developed DREME-MR to jointly reconstruct the reference patient anatomy and 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.
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 decompose 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 an INR-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.
Evaluated using data from a digital phantom (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 1.4±0.9 mm for a lung tumor and 2.5±1.7 mm for the left ventricle. The human study shows good motion correlations (liver: 0.96; left ventricle: 0.65) between DREME-MR-solved motion and extracted surrogate signals.
DREME-MR allows real-time 3D MRI and cardiorespiratory motion tracking with low latency, advancing intra-treatment MR-guided adaptive radiotherapy, including real-time multileaf collimator (MLC) tracking.
基于三维预处理磁共振（MR）扫描，我们开发了DREME-MR，用于联合重建参考患者解剖结构和数据驱动的、针对特定患者的心肺运动模型。通过在重建过程中同时学习的运动编码器，DREME-MR还能够利用最少的治疗中k空间数据进行实时容积MR成像和心肺运动跟踪。
DREME-MR将动态MRI重建和实时MR成像集成到一个统一的双任务学习框架中。从基于三维径向辐条的预处理MR扫描中，DREME-MR使用时空隐式神经表示（INR）来重建预处理动态容积MR图像（学习任务1）。基于INR的重建采用联合图像重建和可变形配准方法，生成参考解剖结构和相应的心肺运动模型。运动模型采用低秩、多分辨率表示，将运动场分解为运动系数和运动基元分量（MBC）的乘积。通过一种渐进的、频率引导策略，DREME-MR将心脏MBC与呼吸MBC解耦，以解析两种不同的运动模式。在进行预处理动态MRI重建的同时，DREME-MR还训练一个基于INR的运动编码器，直接从原始k空间数据推断心肺运动系数（学习任务2），从而能够利用预处理MRI扫描后采集的最少k空间数据（20-30个辐条）进行实时、治疗中容积MR成像和运动跟踪。
使用来自数字体模（XCAT）和人体扫描的数据进行评估，DREME-MR以小于165毫秒的延迟（=150毫秒数据采集+15毫秒推理时间）解决实时三维心肺运动，满足实时成像的时间约束。XCAT研究中，肺肿瘤的质心跟踪平均（±标准差）误差为1.4±0.9毫米，左心室为2.5±1.7毫米。人体研究表明，DREME-MR解决的运动与提取的替代信号之间具有良好的运动相关性（肝脏：0.96；左心室：0.65）。
DREME-MR能够实现低延迟的实时三维MRI和心肺运动跟踪，推动治疗中MR引导的自适应放疗，包括实时多叶准直器（MLC）跟踪。
