当前位置: X-MOL 学术J. Ambient Intell. Smart Environ. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Predicting dose-volume histogram of organ-at-risk using spatial geometric-encoding network for esophageal treatment planning
Journal of Ambient Intelligence and Smart Environments ( IF 1.8 ) Pub Date : 2021-12-14 , DOI: 10.3233/ais-210084
Fudong Nian 1, 2 , Jie Sun 1 , Dashan Jiang 1 , Jingjing Zhang 1 , Teng Li 1 , Wenjuan Lu 3
Affiliation  

Dose-volume histogram (DVH) is an important tool to evaluate the radiation treatment plan quality, which could be predicted based on the distance-volume spatial relationship between planning target volumes (PTV) and organs-at-risks (OARs). However, the prediction accuracy is still limited due to the complicated calculation process and the omission of detailed spatial geometric features. In this paper, we propose a spatial geometric-encoding network (SGEN) to incorporate 3D spatial information with an efficient 2D convolutional neural networks (CNN) for accurate prediction of DVH for esophageal radiation treatments. 3D computed tomography (CT) scans, 3D PTV scans and 3D distance images are used as the multi-view input of the proposed model. The dilation convolution based Multi-scale concurrent Spatial and Channel Squeeze & Excitation (msc-SE) structure in the proposed model not only can maintain comprehensive spatial information with less computation cost, but also can extract the features of organs at different scales effectively. Five-fold cross-validation on 200 intensity-modulated radiation therapy (IMRT) esophageal radiation treatment plans were used in this paper. The mean absolute error (MAE) of DVH focusing on the left lung can achieve 2.73±2.36, while the MAE was 7.73±3.81 using traditional machine learning prediction model. In addition, extensive ablation studies have been conducted and the quantitative results demonstrate the effectiveness of different components in the proposed method.

中文翻译:

使用空间几何编码网络预测危险器官的剂量体积直方图用于食管治疗计划

剂量体积直方图 (DVH) 是评估放射治疗计划质量的重要工具,可以根据计划目标体积 (PTV) 和危险器官 (OAR) 之间的距离-体积空间关系进行预测。然而,由于计算过程复杂,缺少详细的空间几何特征,预测精度仍然受到限制。在本文中,我们提出了一种空间几何编码网络 (SGEN),将 3D 空间信息与高效的 2D 卷积神经网络 (CNN) 相结合,以准确预测食管放射治疗的 DVH。3D 计算机断层扫描 (CT) 扫描、3D PTV 扫描和 3D 距离图像用作所提出模型的多视图输入。基于膨胀卷积的多尺度并发Spatial and Channel Squeeze & 所提出模型中的激励(msc-SE)结构不仅可以以较少的计算成本保持全面的空间信息,而且可以有效地提取不同尺度的器官特征。本文使用了 200 个调强放射治疗 (IMRT) 食管放射治疗计划的五重交叉验证。DVH聚焦左肺的平均绝对误差(MAE)可以达到2.73±2.36,而使用传统机器学习预测模型的MAE为7.73±3.81。此外,已经进行了广泛的消融研究,定量结果证明了所提出方法中不同组件的有效性。还能有效地提取不同尺度器官的特征。本文使用了 200 个调强放射治疗 (IMRT) 食管放射治疗计划的五重交叉验证。DVH聚焦左肺的平均绝对误差(MAE)可以达到2.73±2.36,而使用传统机器学习预测模型的MAE为7.73±3.81。此外,已经进行了广泛的消融研究,定量结果证明了所提出方法中不同组件的有效性。还能有效地提取不同尺度器官的特征。本文使用了 200 个调强放射治疗 (IMRT) 食管放射治疗计划的五重交叉验证。DVH聚焦左肺的平均绝对误差(MAE)可以达到2.73±2.36,而使用传统机器学习预测模型的MAE为7.73±3.81。此外,已经进行了广泛的消融研究,定量结果证明了所提出方法中不同组件的有效性。81 使用传统的机器学习预测模型。此外,已经进行了广泛的消融研究,定量结果证明了所提出方法中不同组件的有效性。81 使用传统的机器学习预测模型。此外,已经进行了广泛的消融研究,定量结果证明了所提出方法中不同组件的有效性。
更新日期:2021-12-14
down
wechat
bug