文献速递中枢神经肿瘤放疗放疗物理与技术

机器学习用于脑肿瘤放疗计划剂量体积直方图临床决策支持系统

Machine learning for dose-volume histogram based clinical decision-making support system in radiation therapy plans for brain tumors.
PubMed 文献 · Clin Transl Radiat Oncol · 2021-09-15

本研究基于79例脑肿瘤患者的VMAT放疗计划(处方总剂量60 Gy),开发机器学习模型对PTV目标是否满足进行分类。逻辑回归模型表现最佳,测试集准确率93.8±4.1%、AUC 0.98±0.02。SHAP分析显示PTV的ΔD99%指标对预测影响最大,模型可辅助放疗计划审批与修改决策。

要点

  • 基于79例脑肿瘤VMAT计划(60 Gy)构建机器学习分类模型。
  • 逻辑回归模型测试集准确率93.8±4.1%、AUC 0.98±0.02。
  • PTV的ΔD99%指标对模型预测影响最大。

核心结论

  • 训练的模型达到满意准确率,可用于医学物理师的数据驱动质量保证项目和放疗医师的计划审批与修改决策支持。
  • 模型解释分析表明模型预测时依赖临床合理的逻辑。

研究设计与样本

  • 基于79例脑肿瘤患者的放疗计划开发机器学习模型,处方总剂量60 Gy,采用VMAT技术。
  • 分析结构包括PTV、脑干、耳蜗和视交叉。
  • 目标变量分类:class-0为PTV治疗计划目标满足的计划,class-1为因优先满足一个或多个危及器官约束而导致PTV目标未满足的计划。
  • 采用双重嵌套交叉验证和AUC指标评估多个模型,选择表现最佳者进一步研究。
  • 使用SHAP交互值解释模型预测。

主要发现

  • 表现最佳的模型为逻辑回归,测试数据准确率93.8±4.1%、AUC 0.98±0.02。
  • SHAP分析显示PTV的ΔD99%指标对模型预测影响最大。
  • 最不重要的特征为左右耳蜗的ΔDMAX。

关键数值与推荐

  • 处方总剂量60 Gy,VMAT技术,分析结构为PTV、脑干、耳蜗和视交叉。
  • 逻辑回归模型测试集准确率93.8±4.1%、AUC 0.98±0.02。

临床怎么用

  • 医学物理师可将模型用于数据驱动的质量保证项目。
  • 放疗医师可利用模型支持治疗计划审批和潜在计划修改的决策。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

PURPOSE: To create and investigate a novel, clinical decision-support system using machine learning (ML). METHODS AND MATERIALS: The ML model was developed based on 79 radiotherapy plans of brain tumor patients that were prescribed a total dose of 60 Gy delivered with volumetric-modulated arc therapy (VMAT). Structures considered for analysis included planning target volume (PTV), brainstem, cochleae, and optic chiasm. The model aimed to classify the target variable that included class-0 corresponding to plans for which the PTV treatment planning objective was met and class-1 that was associated with plans for which the PTV objective was not met due to the priority trade-off to meet one or more organs-at-risk constraints. Several models were evaluated using double-nested cross-validation and an area-under-the-curve (AUC) metric, with the highest performing one selected for further investigation. The model predictions were explained with Shapely additive explanation (SHAP) interaction values. RESULTS: The highest-performing model was Logistic Regression achieving an accuracy of 93.8 ± 4.1% and AUC of 0.98 ± 0.02 on the testing data. The SHAP analysis indicated that the ΔD99% metric for PTV had the greatest influence on the model predictions. The least important feature was ΔDMAX for the left and right cochleae. CONCLUSIONS: The trained model achieved satisfactory accuracy and can be used by medical physicists in a data-driven quality assurance program as well as by radiation oncologists to support their decision-making process in terms of treatment plan approval and potential plan modifications. Model explanation analysis showed that the model relies on clinically valid logic when making predictions.

来源:Clin Transl Radiat Oncol,查看原文。版权归原作者所有。

引用

  1. Siciarz P, Alfaifi S, Uytven EV, et al. Machine learning for dose-volume histogram based clinical decision-making support system in radiation therapy plans for brain tumors. Clin Transl Radiat Oncol. 2021. PMID: 34632117. doi:10.1016/j.ctro.2021.09.001

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。