Department of Radiation Oncology, University of Toledo Medical Center, Toledo, Ohio, USA.
Department of Computer and Data Sciences, Case Western Reserve University, Cleveland, Ohio, USA.
J Appl Clin Med Phys. 2023 Feb;24(2):e13824. doi: 10.1002/acm2.13824. Epub 2022 Dec 9.
This study aims to develop an algorithm to predict gamma passing rate (GPR) in the volumetric-modulated arc therapy (VMAT) technique.
A total of 118 clinical VMAT plans, including 28 mediastina, 25 head and neck, 40 brains intensity-modulated radiosurgery, and 25 prostate cases, were created in RayStation treatment planning system for Edge and TrueBeam linacs. In-house scripts were developed to compute Modulation indices such as plan-averaged beam area (PA), plan-averaged beam irregularity (PI), total monitor unit (MU), leaf travel/arc length, mean dose rate variation, and mean gantry speed variation. Pretreatment verifications were performed on ArcCHECK phantom with SNC software. GPR was calculated with 3%/2 mm and 10% threshold. The dataset was randomly split into a training (70%) and a test (30%) dataset. A random forest regression (RFR) model and support vector regression (SVR) with linear kernel were trained to predict GPR using the complexity metrics as input. The prediction performance was evaluated by calculating the mean absolute error (MAE), R , and root mean square error (RMSE).
RMSEs at γ 3%/2 mm for RFR and SVR were 1.407 ± 0.103 and 1.447 ± 0.121, respectively. MAE was 1.14 ± 0.084 for RFR and 1.101 ± 0.09 for SVR. R was equal to 0.703 ± 0.027 and 0.689 ± 0.053 for RFR and SVR, respectively. GPR of 3%/2 mm with a 10% threshold can be predicted with an error smaller than 3% for 94% of plans using RFR and SVR models. The most important metrics that had the greatest impact on how accurately GPR can be predicted were determined to be the PA, PI, and total MU.
In terms of its prediction values and errors, SVR (linear) appeared to be comparable with RFR for this dataset. Based on our results, the PA, PI, and total MU calculations may be useful in guiding VMAT plan evaluation and ultimately reducing uncertainties in planning and radiation delivery.
本研究旨在开发一种预测容积调强弧形治疗（VMAT）技术中伽马通过率（GPR）的算法。
在 RayStation 治疗计划系统中为 Edge 和 TrueBeam 直线加速器创建了 118 个临床 VMAT 计划，包括 28 个纵隔、25 个头颈部、40 个脑部强度调制放射外科和 25 个前列腺病例。开发了内部脚本来计算调制指数，如计划平均射束面积（PA）、计划平均射束不规则性（PI）、总监测器单位（MU）、叶片行程/弧形长度、平均剂量率变化和平均龙门架速度变化。使用 SNC 软件在 ArcCHECK 体模上进行了预处理验证。使用 3%/2mm 和 10%阈值计算 GPR。数据集随机分为训练（70%）和测试（30%）数据集。使用复杂性指标作为输入，使用随机森林回归（RFR）模型和带有线性核的支持向量回归（SVR）进行训练，以预测 GPR。通过计算平均绝对误差（MAE）、R 和均方根误差（RMSE）来评估预测性能。
RFR 和 SVR 在 γ 3%/2mm 时的 RMSE 分别为 1.407±0.103 和 1.447±0.121。RFR 的 MAE 为 1.14±0.084，SVR 的 MAE 为 1.101±0.09。RFR 和 SVR 的 R 分别为 0.703±0.027 和 0.689±0.053。使用 RFR 和 SVR 模型，可将 3%/2mm 阈值的 GPR 预测误差控制在 3%以内，对 94%的计划进行预测。确定对 GPR 预测精度影响最大的最重要指标是 PA、PI 和总 MU。
就预测值和误差而言，SVR（线性）对于该数据集似乎与 RFR 相当。根据我们的结果，PA、PI 和总 MU 的计算可能有助于指导 VMAT 计划评估，并最终降低计划和辐射传递中的不确定性。
