Lew Kah Seng, Chua Clifford Ghee Ann, Koh Calvin Wei Yang, Lee James Cheow Lei, Park Sung Yong, Tan Hong Qi
Division of Radiation Oncology, National Cancer Centre Singapore, Singapore, Singapore.
Oncology Academic Clinical Programme, Duke-NUS Medical School, Singapore, Singapore.
Front Oncol. 2023 Jan 13;12:1096838. doi: 10.3389/fonc.2022.1096838. eCollection 2022.
This work aims to use machine learning models to predict gamma passing rate of portal dosimetry quality assurance with log file derived features. This allows daily treatment monitoring for patients and reduce wear and tear on EPID detectors to save cost and prevent downtime.
578 VMAT trajectory log files selected from prostate, lung and spine SBRT were used in this work. Four machine learning models were explored to identify the best performing regression model for predicting gamma passing rate within each sub-site and the entire unstratified data. Predictors used in these models comprised of hand-crafted log file-derived features as well as modulation complexity score. Cross validation was used to evaluate the model performance in terms of R and RMSE.
Using gamma passing rate of 1%/1mm criteria and entire dataset, LASSO regression has a R of 0.121 ± 0.005 and RMSE of 4.794 ± 0.013%, SVM regression has a R of 0.605 ± 0.036 and RMSE of 3.210 ± 0.145%, Random Forest regression has a R of 0.940 ± 0.019 and RMSE of 1.233 ± 0.197%. XGBoost regression has the best performance with a R and RMSE value of 0.981 ± 0.015 and 0.652 ± 0.276%, respectively.
Log file-derived features can predict gamma passing rate of portal dosimetry with an average error of less than 2% using the 1%/1mm criteria. This model can potentially be applied to predict the patient specific QA results for every treatment fraction.
本研究旨在使用机器学习模型，通过从日志文件中提取的特征来预测门静脉剂量测定质量保证的伽马通过率。这有助于对患者进行每日治疗监测，减少电子射野影像装置（EPID）探测器的磨损，从而节省成本并防止停机。
本研究使用了从前列腺、肺部和脊柱立体定向放射治疗（SBRT）中选取的578个容积调强弧形治疗（VMAT）轨迹日志文件。探索了四种机器学习模型，以确定在每个子部位以及整个未分层数据中预测伽马通过率的最佳回归模型。这些模型中使用的预测因子包括手工制作的日志文件衍生特征以及调制复杂度得分。采用交叉验证来评估模型在R和均方根误差（RMSE）方面的性能。
使用1%/1mm标准和整个数据集时，套索回归的R值为0.121±0.005，RMSE为4.794±0.013%；支持向量机回归的R值为0.605±0.036，RMSE为3.210±0.145%；随机森林回归的R值为0.940±0.019，RMSE为1.233±0.197%。极端梯度提升（XGBoost）回归性能最佳，R值和RMSE值分别为0.981±0.015和0.652±0.276%。
使用1%/1mm标准时，从日志文件中提取的特征能够预测门静脉剂量测定的伽马通过率，平均误差小于2%。该模型有可能应用于预测每个治疗分次的患者特定质量保证结果。
