Prediction of dosimetric accuracy for VMAT plans using plan complexity parameters via machine learning
Prediction of dosimetric accuracy for VMAT plans using plan complexity parameters via machine learning
复制标题
DOI：
10.1002/mp.13669
复制
发表时间：
2019-07-09
期刊：
影响因子：
3.8
通讯作者：
Mizowaki, Takashi
中科院分区：
文献类型：
--
作者：
Ono, Tomohiro;Hirashima, Hideaki;Mizowaki, Takashi
目的 通过机器学习使用计划复杂性参数来预测容积调制弧形治疗 (VMAT) 计划的剂量精度。方法 数据集包含来自单个机构的 600 例临床 VMAT 计划。每个计划的预测变量 (n = 28) 包括复杂性参数、机器类型和光子束能量。使用螺旋二极管阵列 (ArcCHECK) 进行剂量测量，并使用回归树分析 (RTA)、多元回归分析 (MRA) 和神经网络 (NN) 三种机器学习模型预测 5% 剂量差 (DD5%) 和 3%/3 mm 伽马指数 (gamma 3%/3 mm) 的通过率的剂量测量精度。首先，将预测模型应用于 500 个 VMAT 计划案例。然后，使用每个模型对剩余 100 个案例（评估数据集）的剂量测定精度进行预测。评估预测和测量的通过率之间的误差。结果 对于 600 个案例，DD5% 和 gamma 3%/3 mm 的测量通过率的平均+/-标准偏差分别为 92.3% +/- 9.1% 和 96.8% +/- 3.1%。对于评估数据集，DD5% 和 gamma 3%/3 mm 的预测误差的平均值+/-标准差对于 RTA 为 0.5% +/- 3.0% 和 0.6% +/- 2.4%，对于 MRA 为 0.0% +/- 2.9% 和 0.5% +/- 2.4%，对于 NN 为 -0.2% +/- 2.7% 和 -0.2% +/- 2.1%，分别。结论 就预测误差而言，NN 的表现略优于 RTA 和 MRA。这些发现可能有助于提高针对患者的质量保证程序的效率。
Purpose The dosimetric accuracies of volumetric modulated arc therapy (VMAT) plans were predicted using plan complexity parameters via machine learning. Methods The dataset consisted of 600 cases of clinical VMAT plans from a single institution. The predictor variables (n = 28) for each plan included complexity parameters, machine type, and photon beam energy. Dosimetric measurements were performed using a helical diode array (ArcCHECK), and the dosimetric accuracy of the passing rates for a 5% dose difference (DD5%) and gamma index of 3%/3 mm (gamma 3%/3 mm) were predicted using three machine learning models: regression tree analysis (RTA), multiple regression analysis (MRA), and neural networks (NNs). First, the prediction models were applied to 500 cases of the VMAT plans. Then, the dosimetric accuracy was predicted using each model for the remaining 100 cases (evaluation dataset). The error between the predicted and measured passing rates was evaluated. Results For the 600 cases, the mean +/- standard deviation of the measured passing rates was 92.3% +/- 9.1% and 96.8% +/- 3.1% for DD5% and gamma 3%/3 mm, respectively. For the evaluation dataset, the mean +/- standard deviation of the prediction errors for DD5% and gamma 3%/3 mm was 0.5% +/- 3.0% and 0.6% +/- 2.4% for RTA, 0.0% +/- 2.9% and 0.5% +/- 2.4% for MRA, and -0.2% +/- 2.7% and -0.2% +/- 2.1% for NN, respectively. Conclusions NNs performed slightly better than RTA and MRA in terms of prediction error. These findings may contribute to increasing the efficiency of patient-specific quality-assurance procedures.