Department of Radiation Oncology, National Clinical Research Center for Cancer/Cancer Hospital, National Cancer Center, Chinese Academy of Medical Sciences and Peking Union Medical College, 17 Panjiayuannanli Rd., Chaoyang Dist, Beijing, 100021, China.
Radiat Oncol. 2024 Oct 10;19(1):141. doi: 10.1186/s13014-024-02534-2.
Volumetric modulated arc therapy (VMAT) planning optimization involves iterative adjustment of numerous parameters, and hence requires repeatedly dose recalculation. In this study, we used the deep learning method to develop a fast and accurate dose calculation method for VMAT.
The classical 3D UNet was adopted and trained to learn the physics principle of dose calculation. The inputs included the projected fluence map (FM), computed tomography (CT) images, the radiological depth and the source-to-voxel distance (SVD). The projected FM was generated by projecting the accumulated FM between two consecutive control points (CPs) onto the patient's anatomy. The accumulated FM was calculated by simulating the movement of the multi-leaf collimator (MLC) from one CP to the next. The dose, calculated by the treatment planning system (TPS), was used as ground truth. 51 head and neck VMAT plans were used, with 43, 1 and 7 cases as training, validation, and testing datasets, respectively. Correspondingly, 7182, 180 and 1260 CP samples were included in the training, validation, and testing datasets.
This presented method was evaluated by comparing the derived dose distribution to the TPS calculated dose distribution. The dose profiles coincided for both the single CP and the entire plan (summation of all CPs). But the network derived dose was smoother than the TPS calculated dose. Gamma analysis was performed between the network derived dose and the TPS calculated dose. The average gamma pass rate was 96.56%, 98.75%, 98.03% and 99.30% under the criteria of 2% (tolerance) -2 mm (distance to agreement, DTA). 2%-3 mm, 3%-2 mm and 3%-3 mm. No significant difference was observed on the critical indices including the max, mean dose, and the relative volume covered by the 2000 cGy, 4000 cGy and the prescription dose. For one CP, the average computational time of the network and TPS was 0.09s and 0.53s. And for one patient, the average time was 16.51s and 95.60s.
The dose distribution derived by the network showed good agreement with the TPS calculated dose distribution. The computational time was reduced to approximate one-sixth of its original duration. Therefore the presented deep learning-based dose calculation method has the potential to be used for planning optimization.
容积调强弧形治疗（VMAT）计划优化涉及大量参数的迭代调整，因此需要反复剂量计算。在这项研究中，我们使用深度学习方法开发了一种快速准确的 VMAT 剂量计算方法。
采用经典的 3D UNet 进行训练，以学习剂量计算的物理原理。输入包括投影剂量分布（FM）、计算机断层扫描（CT）图像、放射深度和源到体素距离（SVD）。投影 FM 通过将两个连续控制点（CP）之间的累积 FM 投影到患者解剖结构上生成。累积 FM 通过模拟多叶准直器（MLC）从一个 CP 到下一个 CP 的运动来计算。由治疗计划系统（TPS）计算的剂量用作地面真值。使用 51 个头颈部 VMAT 计划，其中 43、1 和 7 例分别作为训练、验证和测试数据集。相应地，训练、验证和测试数据集中分别包含 7182、180 和 1260 个 CP 样本。
通过比较网络推导的剂量分布与 TPS 计算的剂量分布，对所提出的方法进行了评估。单个 CP 和整个计划（所有 CP 的总和）的剂量分布都吻合。但是，网络推导的剂量比 TPS 计算的剂量更平滑。在 2%（公差）-2mm（符合距离，DTA）、2%-3mm、3%-2mm 和 3%-3mm 的标准下，对网络推导的剂量和 TPS 计算的剂量进行了伽马分析。平均伽马通过率分别为 96.56%、98.75%、98.03%和 99.30%。在最大、平均剂量以及 2000cGy、4000cGy 和处方剂量覆盖的相对体积等关键指标上，没有观察到显著差异。对于一个 CP，网络和 TPS 的平均计算时间分别为 0.09s 和 0.53s。对于一个患者，平均时间分别为 16.51s 和 95.60s。
网络推导的剂量分布与 TPS 计算的剂量分布吻合良好。计算时间减少到原来的大约六分之一。因此，所提出的基于深度学习的剂量计算方法有可能用于计划优化。
