Predicting radiation treatment planning evaluation parameter using artificial intelligence and machine learning

Abstract

Purpose: This study suggested a new method predicting the dose-volume parameter for radiation treatment planning evaluation using machine learning, and to evaluate the performance of different learning algorithms in the parameter prediction. Methods: Dose distribution index (DDI) for fifty prostate volumetric modulated arc therapy plans were calculated, and compared to results predicted by machine learning using algorithms, namely, linear regression, tree regression, support vector machine (SVM) and Gaussian process regression (GPR). Root mean square error (RMSE), prediction speed and training time were determined to evaluate the performance of each algorithm. Results: From the results, it is found that the square exponential GPR algorithm had the smallest RMSE, relatively high prediction speed and short training time of 0.0038, 4,100 observation/s and 0.18 s, respectively. All linear regression, SVM and GPR algorithms performed well according to their RMSE in the range of 0.0038–0.0193. However, RMSE of the medium and coarse tree regression algorithms were found larger than 0.03, showing that they are not suitable for predicting DDI in this study. Conclusion: Machine learning can be used to predict dose-volume parameter such as DDI in radiation treatment planning QA. Selection of a suitable machine learning algorithm is important to determine the parameter effectively.

Evaluation of dose-volume histogram prediction for organ-at risk and planning target volume based on machine learning

“…In the field of radiotherapy, making dose-volume histogram (DVH) or dose distribution of organ at risk (OAR) predictions based on prior plan data could provide a valuable dose-volume reference that could help planners determine whether the quality of a treatment plan could be further improved [3][4][5][6][7][8][9][10][11] and could be used as the dose-volume optimization input constraints in a treatment planning system (TPS) to assist in plan generation [12][13][14][15][16][17] . In addition, a machine learning method could predict the dose-volume parameter such as dose distribution index for treatment plan evaluation which is helpful for fast plan quality evaluation 18 .…”

Machine Learning in Healthcare Communication

“…Machine learning can predict dose-volume parameters, such as the dose distribution index in radiation treatment planning quality assurance. In order to determine the parameter efficiently and effectively, the machine learning algorithm needs to be selected appropriately with performance, as shown in Table 2 [65]. Telehealth or telemedicine is health resources or services administered through telecommunications or electronic information technologies.…”

“…Table summarizingthe root mean square error (RMSE), R-squared, prediction speed, and training time of models created in the Regression Learning App available in the MATLAB's Machine Learning and Statistical Toolbox, using five dose-volume points from each dose-volume histogram (DVH) with 4-fold cross validation. They are ordered from the best performance to worst[65].…”

Probabilistic feature extraction, dose statistic prediction and dose mimicking for automated radiation therapy treatment planning

“…In general, automated treatment planning using machine learning, also known as knowledge-based planning, concerns the automatic plan generation using knowledge extracted from historically delivered clinical treatment plans. [3][4][5][6] One usually goes about this task by first assuming a parameterized optimization problem and then training a machine learning model to predict the unknown parameters, which is done in such a way that the solution to the resulting optimization problem will correspond to a clinically satisfactory plan. An example is the prediction of weights in a weighted-sum formulation, 7 which may even be sequentially adjusted by an agent trained using reinforcement learning methods.…”