Department of Radiation Oncology, University of Washington School of Medicine, Seattle, Washington, USA.
Raysearch Laboratories, Stockholm, Sweden.
J Appl Clin Med Phys. 2023 Oct;24(10):e14065. doi: 10.1002/acm2.14065. Epub 2023 Jun 19.
The purpose of this study is to investigate the use of a deep learning architecture for automated treatment planning for proton pencil beam scanning (PBS).
A 3-dimensional (3D) U-Net model has been implemented in a commercial treatment planning system (TPS) that uses contoured regions of interest (ROI) binary masks as model inputs with a predicted dose distribution as the model output. Predicted dose distributions were converted to deliverable PBS treatment plans using a voxel-wise robust dose mimicking optimization algorithm. This model was leveraged to generate machine learning (ML) optimized plans for patients receiving proton PBS irradiation of the chest wall. Model training was carried out on a retrospective set of 48 previously-treated chest wall patient treatment plans. Model evaluation was carried out by generating ML-optimized plans on a hold-out set of 12 contoured chest wall patient CT datasets from previously treated patients. Clinical goal criteria and gamma analysis were used to compare dose distributions of the ML-optimized plans against the clinically approved plans across the test patients.
Statistical analysis of mean clinical goal criteria indicates that compared to the clinical plans, the ML optimization workflow generated robust plans with similar dose to the heart, lungs, and esophagus while achieving superior dosimetric coverage to the PTV chest wall (clinical mean V95 = 97.6% vs. ML mean V95 = 99.1%, p < 0.001) across the 12 test patients.
ML-based automated treatment plan optimization using the 3D U-Net model can generate treatment plans of similar clinical quality compared to human-driven optimization.
本研究旨在探讨深度学习架构在质子笔束扫描（PBS）自动治疗计划中的应用。
在商业治疗计划系统（TPS）中实现了一个 3 维（3D）U-Net 模型，该模型使用感兴趣区域（ROI）轮廓二进制掩模作为模型输入，以预测剂量分布作为模型输出。预测剂量分布通过使用基于体素的稳健剂量模拟优化算法转换为可交付的 PBS 治疗计划。该模型用于为接受质子 PBS 胸部照射的患者生成机器学习（ML）优化治疗计划。模型训练是在一组 48 例先前治疗的胸壁患者治疗计划的回顾性数据集上进行的。模型评估是通过在一组来自先前治疗患者的 12 个轮廓胸部 CT 数据集上生成 ML 优化计划来进行的。使用临床目标标准和伽马分析来比较测试患者的 ML 优化计划与临床批准计划的剂量分布。
平均临床目标标准的统计分析表明，与临床计划相比，ML 优化工作流程生成了稳健的计划，对心脏、肺和食管的剂量相似，同时对胸壁 PTV 的剂量覆盖更好（临床平均 V95=97.6%比 ML 平均 V95=99.1%，p<0.001）在 12 名测试患者中。
使用 3D U-Net 模型的基于 ML 的自动治疗计划优化可以生成与人工驱动优化相似的临床质量的治疗计划。
