Shanghai Chest Hospital, School of Medicine, Shanghai Jiao Tong University, 200030, Shanghai, China.
Department of Radiation Oncology, The First Affiliated Hospital of Zhengzhou University, Henan, China.
Strahlenther Onkol. 2023 May;199(5):498-510. doi: 10.1007/s00066-023-02076-8. Epub 2023 Mar 29.
To identify delivery error type and predict associated error magnitude by image-based features using machine learning (ML).
In this study, a total of 40 thoracic plans (including 208 beams) were selected, and four error types with different magnitudes were introduced into the original plans, including 1) collimator misalignment (COLL), 2) monitor unit (MU) variation, 3) systematic multileaf collimator misalignment (MLCS), and 4) random MLC misalignment (MLCR). These dose distributions of portal dose predictions for the original plans were defined as the reference dose distributions (RDD), while those for the error-introduced plans were defined as the error-introduced dose distributions (EDD). Both distributions were calculated for all beams with portal dose image prediction (PDIP). Besides, 14 image-based features were extracted from RDD and EDD of portal dose predictions to obtain the feature vectors. In addition, a random forest was adopted for the multiclass classification task, and regression prediction for error magnitude.
The top five features extracted with the highest weight included 1) the relative displacement in the x direction, 2) the ratio of the absolute minimum residual error to the maximal RDD value, 3) the product of the maximum and minimum residuals, 4) the ratio of the absolute maximum residual error to the maximal RDD value, and 5) the ratio of the absolute mean residual value to the maximal RDD value. The relative displacement in the x direction had the highest weight. The overall accuracy of the five-class classification model was 99.85% for the validation set and 99.30% for the testing set. This model could be applied to the classification of the error-free plan, COLL, MU, MLCS, and MLCR with an accuracy of 100%, 98.4%, 99.9%, 98.0%, and 98.3%, respectively. MLCR had the worst performance in error magnitude prediction (70.1-96.6%), while others had better performance in error magnitude prediction (higher than 93%). In the error magnitude prediction, the mean absolute error (MAE) between predicted error magnitude and actual error ranged from 0.03 to 0.33, with the root mean squared error (RMSE) varying from 0.17 to 0.56 for the validation set. The MAE and RMSE ranged from 0.03 to 0.50 and 0.44 to 0.59 for the test set, respectively.
It could be demonstrated in this study that the image-based features extracted from RDD and EDD can be employed to identify different types of delivery errors and accurately predict error magnitude with the assistance of ML techniques. They can be used to associate traditional gamma analysis with clinically based analysis for error classification and magnitude prediction in patient-specific IMRT quality assurance.
通过基于图像的特征，利用机器学习（ML）识别和预测与传输误差类型和相关误差幅度相关的信息。
本研究共选择了 40 个胸部计划（包括 208 个射束），并将四种不同大小的误差类型引入原始计划中，包括 1）准直器失准（COLL），2）监测器单位（MU）变化，3）系统多叶准直器失准（MLCS）和 4）随机多叶准直器失准（MLCR）。将原始计划的这些剂量分布的端口剂量预测定义为参考剂量分布（RDD），而将引入误差的计划的剂量分布定义为引入误差的剂量分布（EDD）。所有射束均采用端口剂量图像预测（PDIP）计算这两种分布。此外，从 RDD 和 EDD 中提取了 14 个基于图像的特征，以获得特征向量。此外，采用随机森林进行多类分类任务，并对误差幅度进行回归预测。
基于最高权重提取的前五个特征包括 1）x 方向的相对位移，2）绝对最小剩余误差与最大 RDD 值之比，3）最大和最小残差的乘积，4）绝对最大残差与最大 RDD 值之比，5）绝对平均残差与最大 RDD 值之比。x 方向的相对位移具有最高的权重。验证集的五分类模型的总体准确率为 99.85%，测试集的准确率为 99.30%。该模型可应用于无误差计划、COLL、MU、MLCS 和 MLCR 的分类，准确率分别为 100%、98.4%、99.9%、98.0%和 98.3%。MLCR 在误差幅度预测方面的性能最差（70.1-96.6%），而其他方面的性能在误差幅度预测方面更好（均高于 93%）。在误差幅度预测中，预测误差幅度与实际误差之间的平均绝对误差（MAE）在 0.03 到 0.33 之间，验证集的均方根误差（RMSE）在 0.17 到 0.56 之间。测试集的 MAE 和 RMSE 分别在 0.03 到 0.50 和 0.44 到 0.59 之间。
本研究表明，从 RDD 和 EDD 中提取的基于图像的特征可用于识别不同类型的传输误差，并借助 ML 技术准确预测误差幅度。它们可用于将传统的伽马分析与基于临床的分析相结合，用于患者特定的调强放射治疗质量保证中的误差分类和幅度预测。
