Abstract：
MRI-guided radiotherapy systems enable beam gating by tracking the target on planar, two-dimensional cine images acquired during treatment. This study aims to evaluate how deep-learning (DL) models for target tracking that are trained on data from one fraction can be translated to subsequent fractions. Cine images were acquired for six patients treated on an MRI-guided radiotherapy platform (MRIdian, Viewray Inc.) with an onboard 0.35 T MRI scanner. Three DL models (U-net, attention U-net and nested U-net) for target tracking were trained using two training strategies: (1) uniform training using data obtained only from the first fraction with testing performed on data from subsequent fractions and (2) adaptive training in which training was updated each fraction by adding 20 samples from the current fraction with testing performed on the remaining images from that fraction. Tracking performance was compared between algorithms, models and training strategies by evaluating the Dice similarity coefficient (DSC) and 95% Hausdorff Distance (HD95) between automatically generated and manually specified contours. The mean DSC for all six patients in comparing manual contours and contours generated by the onboard algorithm (OBT) were 0.68 ± 0.16. Compared to OBT, the DSC values improved 17.0 - 19.3% for the three DL models with uniform training, and 24.7 - 25.7% for the models based on adaptive training. The HD95 values improved 50.6 - 54.5% for the models based on adaptive training. DL-based techniques achieved better tracking performance than the onboard, registration-based tracking approach. DL-based tracking performance improved when implementing an adaptive strategy that augments training data fraction-by-fraction.
摘要：
MRI引导的放射治疗系统通过跟踪平面上的目标来实现波束门控，在治疗期间采集的二维电影图像。这项研究旨在评估如何在一个部分的数据上训练的用于目标跟踪的深度学习（DL）模型可以转换为后续部分。获得了在MRI引导的放射治疗平台上治疗的六名患者的电影图像（MRIdian，ViewrayInc.）带有机载0.35TMRI扫描仪。三种DL模型(U-net，使用两种训练策略训练用于目标跟踪的注意力U网和嵌套U网）：（1）使用仅从第一个部分获得的数据进行统一训练，并对后续部分的数据进行测试；（2）自适应训练通过从当前部分添加20个样本并对该部分的剩余图像进行测试来更新每个部分。比较了算法之间的跟踪性能，模型和训练策略，通过评估自动生成和手动指定轮廓之间的骰子相似系数（DSC）和95％Hausdorff距离（HD95）。在比较手动轮廓和通过机载算法（OBT）生成的轮廓时，所有六名患者的平均DSC为0.68±0.16。与OBT相比，对于三个具有统一训练的DL模型，DSC值提高了17.0-19.3%，基于自适应训练的模型为24.7-25.7%。基于自适应训练的模型的HD95值提高了50.6-54.5%。基于DL的技术实现了比机载更好的跟踪性能，基于注册的跟踪方法。基于DL的跟踪性能在实施自适应策略时得到了改善，该策略可逐级增强训练数据。
