基于机器学习的质子铅笔束扫描递送误差预测框架，使用辐照日志文件。

A machine learning-based framework for delivery error prediction in proton pencil beam scanning using irradiation log-files.

机构信息

Seattle Cancer Care Alliance Proton Therapy Center, 1570 N 115th St., Seattle, WA 98133, USA; Centre for Medical Radiation Physics, University of Wollongong, Wollongong, NSW 2500, Australia.

Seattle Cancer Care Alliance Proton Therapy Center, 1570 N 115th St., Seattle, WA 98133, USA; Department of Radiation Oncology, University of Washington School of Medicine, 1959 NE Pacific St., Seattle, WA 98195, USA; Department of Radiology, University of Washington School of Medicine, 1959 NE Pacific St., Seattle, WA 98195, USA.

出版信息

Phys Med. 2020 Oct;78:179-186. doi: 10.1016/j.ejmp.2020.09.008. Epub 2020 Oct 7.

DOI:10.1016/j.ejmp.2020.09.008

PMID:33038643

Abstract

PURPOSE

This study aims to investigate the use of machine learning models for delivery error prediction in proton pencil beam scanning (PBS) delivery.

METHODS

A dataset of planned and delivered PBS spot parameters was generated from a set of 20 prostate patient treatments. Planned spot parameters (spot position, MU and energy) were extracted from the treatment planning system (TPS) for each beam. Delivered spot parameters were extracted from irradiation log-files for each beam delivery following treatment. The dataset was used as a training dataset for three machine learning models which were trained to predict delivered spot parameters based on planned parameters. K-fold cross validation was employed for hyper-parameter tuning and model selection where the mean absolute error (MAE) was used as the model evaluation metric. The model with lowest MAE was then selected to generate a predicted dose distribution for a test prostate patient within a commercial TPS.

RESULTS

Analysis of the spot position delivery error between planned and delivered values resulted in standard deviations of 0.39 mm and 0.44 mm for x and y spot positions respectively. Prediction error standard deviation values of spot positions using the selected model were 0.22 mm and 0.11 mm for x and y spot positions respectively. Finally, a three-way comparison of dose distributions and DVH values for select OARs indicates that the random-forest-predicted dose distribution within the test prostate patient was in closer agreement to the delivered dose distribution than the planned distribution.

CONCLUSIONS

PBS delivery error can be accurately predicted using machine learning techniques.

摘要

目的

本研究旨在探讨机器学习模型在质子铅笔束扫描（PBS）治疗中的递送误差预测中的应用。

方法

从 20 例前列腺患者的治疗中生成了一个计划和递送的 PBS 点参数数据集。从每个射束的治疗计划系统（TPS）中提取了计划的点参数（点位置、MU 和能量）。从每个射束的辐照日志文件中提取了递送的点参数。该数据集被用作三个机器学习模型的训练数据集，这些模型被训练用于根据计划参数预测递送的点参数。采用 K 折交叉验证进行超参数调整和模型选择，以平均绝对误差（MAE）作为模型评估指标。选择 MAE 最低的模型来为商业 TPS 内的一个测试前列腺患者生成预测剂量分布。

结果

计划和递送的点位置之间的位置传递误差分析导致 x 和 y 点位置的标准偏差分别为 0.39mm 和 0.44mm。使用选定模型的点位置预测误差标准偏差值分别为 0.22mm 和 0.11mm。最后，对选择的 OAR 的剂量分布和 DVH 值进行了三向比较，表明在测试前列腺患者中，随机森林预测的剂量分布与递送剂量分布的一致性优于计划分布。