| 晋國棟,刘宇翔,杨碧凝,等.利用Informer深度学习网络预测呼吸运动[J].中华放射医学与防护杂志,2023,43(7):513-517.Jin Guodong,Liu Yuxiang,Yang Bining,et al.Predicting respiratory motion using an Informer deep learning network[J].Chin J Radiol Med Prot,2023,43(7):513-517 |
| 利用Informer深度学习网络预测呼吸运动 |
| Predicting respiratory motion using an Informer deep learning network |
| 投稿时间：2022-11-20 |
| DOI：10.3760/cma.j.cn112271-20221120-00451 |
| 中文关键词: 呼吸运动|深度学习|时间序列预测 |
| 英文关键词:Respiratory motion|Deep learning|Time series forecasting |
| 基金项目:国家自然科学基金(12175312);北京市科技新星计划(Z201100006820058) |
|
| 摘要点击次数: 4643 |
| 全文下载次数: 1087 |
| 中文摘要: |
| 目的 研究时间序列深度学习方法预测呼吸运动。方法 纳入肺癌患者的呼吸运动数据80例,将每一例呼吸运动数据按8∶2的比例划分为训练集和测试集,深度学习采用Informer网络,预测约600 ms延迟的呼吸运动,采用归一化均方根误差(nRMSE)和相对均方根误差(rRMSE)评估模型性能。结果 Informer的整体效果优于常规的多层感知器(MLP)和长短期记忆(LSTM)模型。在423 ms的预测时间下,Informer模型的平均nRMSE和rRMSE分别为0.270和0.365;在615 ms的预测时间下,平均nRMSE和rRMSE分别为0.380和0.379。结论 采用的Informer模型在预测时间较长时有较好的效果,对提高实时跟踪技术的效果具有潜在应用价值。 |
| 英文摘要: |
| Objective To investigate a time series deep learning model for respiratory motion prediction. Methods Eighty pieces of respiratory motion data from lung cancer patients were used in this study. They were divided into a training set and a test set at a ratio of 8∶2. The Informer deep learning network was employed to predict the respiratory motions with a latency of about 600 ms. The model performance was evaluated based on normalized root mean square errors (nRMSEs) and relative root mean square errors (rRMSEs). Results The Informer model outperformed the conventional multilayer perceptron (MLP) and long short-term memory (LSTM) models. The Informer model yielded an average nRMSE and rRMSE of 0.270 and 0.365, respectively, at a prediction time of 423 ms, and 0.380 and 0.379, respectively, at a prediction time of 615 ms. Conclusions The Informer model performs well in the case of a longer prediction time and has potential application value for improving the effects of the real-time tracking technology. |
| HTML 查看全文 查看/发表评论 下载PDF阅读器 |
| 关闭 |
|
|
|