Dose prediction using a deep neural network for accelerated planning of rectal cancer radiotherapy
Dose prediction using a deep neural network for accelerated planning of rectal cancer radiotherapy
复制标题
使用深度神经网络进行剂量预测以加速直肠癌放射治疗计划
DOI：
10.1016/j.radonc.2020.05.005
复制
发表时间：
2020-08-01
影响因子：
5.7
通讯作者：
Yi, Zhang
中科院分区：
文献类型：
--
作者：
Song, Ying;Hu, Junjie;Yi, Zhang
目的：应用深度神经网络预测直肠癌患者的剂量分布，以加速体积调制弧技术（VMAT）planning.Materials和方法：随机选择2018年2月至2019年4月接受治疗的187例患者的计算机断层扫描和批准的VMAT计划以及剂量（批准）进行这项回顾性研究。深度神经网络DeepLabv 3+用于剂量分布预测。介绍了一种基于先验剂量信息的计划方案。采用配对t检验，通过均方误差（MSE）、标准化剂量差（Δ D）和剂量体积直方图（DVH）指数评价预测精度。信息辅助和经验丰富的重新计划分别由1年和6年经验丰富的剂量测定师进行。结果：DeepLabv 3+预测结果（Dose（DeepLabv 3+））均符合临床要求。以剂量（获批）为基线，MSE为0.001，平均6D为0.40%，剂量（DeepLabv 3+）的四分位数间距为0.079%-0.30%。除符合性指数外，未发现剂量（获批）和剂量（DeepLabv 3+）之间的计划靶体积定量参数存在显著差异。双向方差分析显示，信息辅助再计划与经验再计划的再计划时间有显著性差异，最大节省时间为15.76 min。信息辅助再计划的优点是最大剂量低、最小剂量高、均匀性指数低，缺点是适形性指数低、机器单位数高，差异有显著性。DeepLabv 3+成功预测了直肠癌剂量分布，预测的先验信息帮助多水平经验丰富的剂量学家节省了计划时间。(C)2020 Elsevier B. V.保留所有权利。
Purpose: To apply a deep neural network to predict dose distributions of rectal cancer patients for accelerated volume modulated arc technique (VMAT) planning.Materials and methods: Computed tomography scans and approved VMAT plans together with Dose(approved) of 187 patients treated from February 2018 to April 2019 were randomly selected for this retrospective study. The deep neural network DeepLabv3+ was applied for dose distribution prediction. A prior dose information-aided planning scheme was introduced. Prediction precision was evaluated by mean square error (MSE), normalized dose difference (delta D), and dose-volume histogram (DVH) indices using a paired t test. Information-aided and experienced replanning were performed by 1-year and 6-year experienced dosimetrists, respectively. Replanning time and DVH indices were evaluated by two-way variance analysis.Results: The DeepLabv3+ prediction results (Dose(DeepLabv3+)) were all clinically acceptable. Taking Dose(approved )as the baseline, the MSE was 0.001 and mean 6D was 0.40% with an inter-quartile range of 0.079%-0.30% for Dose(DeepLabv3+). No significant differences were found for the planning target volume quantitative parameters between Dose(approved) and Dose(DeepLabv3+), except for the conformality index. For the two-way variance analysis, a significantly different replanning time was found between the information-aided and experienced replanning with maximum time-saving of 15.76 min. Information-aided replans had the advantage of lower maximum dose, higher minimum dose, and lower homogeneity index, and the disadvantage of lower conformality index and higher machine unites with significant differences.Conclusion: DeepLabv3+ successfully predicted rectal cancer dose distribution, and the predicted prior information helped save planning times for multi-level experienced dosimetrists. (C) 2020 Elsevier B.V. All rights reserved.