Hunt Brady, Gill Gobind S, Alexander Daniel A, Streeter Samuel S, Gladstone David J, Russo Gregory A, Zaki Bassem I, Pogue Brian W, Zhang Rongxiao
Thayer School of Engineering, Dartmouth College, Hanover, New Hampshire; Geisel School of Medicine, Dartmouth College, Hanover, New Hampshire; Dartmouth Cancer Center, Dartmouth-Hitchcock Medical Center, Lebanon, New Hampshire.
Dartmouth Cancer Center, Dartmouth-Hitchcock Medical Center, Lebanon, New Hampshire.
Int J Radiat Oncol Biol Phys. 2023 Mar 15;115(4):983-993. doi: 10.1016/j.ijrobp.2022.09.086. Epub 2022 Oct 26.
We developed a deep learning (DL) model for fast deformable image registration using 2-dimensional sagittal cine magnetic resonance imaging (MRI) acquired during radiation therapy and evaluated its potential for real-time target tracking compared with conventional image registration methods.
Our DL model uses a pair of cine MRI images as input and provides a motion vector field (MVF) as output. The MVF is then applied to align the input images. A retrospective study was conducted to train and evaluate our model using cine MRI data from patients undergoing treatment for abdominal and thoracic tumors. For each treatment fraction, MR-linear accelerator delivery log files, tracking videos, and cine image files were analyzed. Individual MRI frames were temporally sampled to construct a large set of image registration pairs used to evaluate multiple methods. The DL model was optimized using 5-fold cross validation, and model outputs (transformed images and MVFs) using test set images were saved for comparison with 3 conventional registration methods (affine, b-spline, and demons). Evaluation metrics were 3-fold: (1) registration error, (2) MVF stability (both spatial and temporal), and (3) average computation time.
We analyzed >21 hours of cine MRI (>629,000 frames) acquired during 86 treatment fractions from 21 patients. In a test set of 10,320 image registration pairs, DL registration outperformed conventional methods in both registration error (affine, b-spline, demons, DL; root mean square error: 0.067, 0.040, 0.036, 0.032; paired t test demons vs DL: t[20] = 4.2, P < .001) and computation time per frame (51, 1150, 4583, 8 ms). Among deformable methods, spatial stability of resulting MVFs was comparable; however, the DL model had significantly improved temporal consistency.
DL-based image registration can leverage large-scale MR cine data sets to outperform conventional registration methods and is a promising solution for real-time deformable motion estimation in radiation therapy.
我们开发了一种深度学习（DL）模型，用于使用放射治疗期间获取的二维矢状位电影磁共振成像（MRI）进行快速可变形图像配准，并与传统图像配准方法相比，评估其在实时目标跟踪方面的潜力。
我们的DL模型使用一对电影MRI图像作为输入，并提供运动矢量场（MVF）作为输出。然后应用MVF来对齐输入图像。进行了一项回顾性研究，使用来自接受腹部和胸部肿瘤治疗患者的电影MRI数据来训练和评估我们的模型。对于每个治疗分次，分析了MR直线加速器输送日志文件、跟踪视频和电影图像文件。对单个MRI帧进行时间采样，以构建用于评估多种方法的大量图像配准对。使用五折交叉验证对DL模型进行优化，并保存使用测试集图像的模型输出（变换后的图像和MVF），以便与三种传统配准方法（仿射、B样条和 demons）进行比较。评估指标有三个方面：（1）配准误差，（2）MVF稳定性（空间和时间方面），以及（3）平均计算时间。
我们分析了来自21名患者的86个治疗分次期间获取的超过21小时的电影MRI（超过629,000帧）。在10,320个图像配准对的测试集中，DL配准在配准误差（仿射、B样条、demons、DL；均方根误差：0.067、0.040、0.036、0.032；配对t检验，demons与DL比较：t[20] = 4.2，P <.001）和每帧计算时间（51、1150、4583、8毫秒）方面均优于传统方法。在可变形方法中，所得MVF的空间稳定性相当；然而，DL模型的时间一致性有显著改善。
基于DL的图像配准可以利用大规模MR电影数据集来超越传统配准方法，并且是放射治疗中实时可变形运动估计的一种有前景的解决方案。
