董顺成,孙彦泽,杨悦,杜永欢,张佩毅,昂文胜,文万信.基于卷积神经网络的立体闪烁光三维剂量重建研究[J].中华放射医学与防护杂志,2023,43(12):1034-1040
基于卷积神经网络的立体闪烁光三维剂量重建研究
Convolutional neural network-based three-dimensional dose reconstruction using volumetric scintillation light
投稿时间:2023-04-10  
DOI:10.3760/cma.j.cn112271-20230410-00113
中文关键词:  卷积神经网络  三维剂量  辐射发光
英文关键词:Convolutional neural networks  3D dosimetry  Radioluminescence
基金项目:
作者单位E-mail
董顺成 苏州大学放射医学与防护学院, 苏州 215031  
孙彦泽 苏州大学附属第二医院放射治疗科, 苏州 215004  
杨悦 复旦大学附属中山医院放射治疗科, 上海 200032  
杜永欢 苏州大学放射医学与防护学院, 苏州 215031  
张佩毅 苏州大学放射医学与防护学院, 苏州 215031  
昂文胜 苏州大学放射医学与防护学院, 苏州 215031  
文万信 苏州大学放射医学与防护学院, 苏州 215031 wxwen@suda.edu.cn 
摘要点击次数: 647
全文下载次数: 242
中文摘要:
      目的 基于卷积神经网络(convolutional neural networks, CNN)对多视角闪烁光处理,重建放射治疗中三维相对剂量分布。方法 利用互补金属氧化物半导体(CMOS)成像传感器捕获正交三视角的荧光图像,将荧光图像转化为三维图像,输入已训练的卷积神经网络中进行剂量重建,分别评估不同射野重建剂量的伽马通过率、均方误差(MSE)、百分深度剂量(PDD)曲线和横向剂量分布(CBP)曲线。卷积神经网络模型为3D-Unet,其预先在虚拟数据集上进行训练。结果 以50%最大剂量为阈值,3%/3mm为标准,所有射野重建分布中心层面伽马通过率和立体平均伽马通过率均超过90%,均方误差维持在1%以下。所有射野重建分布的PDD曲线均方误差在1‰以下,CBP曲线均方误差在1%以下。结论 本研究实现了一种基于深度学习的三维闪烁光重建方法,完善了基于塑料闪烁体的瞬时三维相对剂量验证。
英文摘要:
      Objective To reconstruct the three-dimensional (3D) dose distribution in radiotherapy based on the convolutional neural networks (CNN) through multi-perspective scintillation light processing.Methods First, fluorescence images were captured from three orthogonal perspectives using a complementary metal-oxide-semiconductor (CMOS) imaging sensor. Then, the images were converted into 3D images, which were input to the trained CNN for dose reconstruction. Finally, the reconstructed doses in different fields were evaluated in terms of gamma pass rate, mean-square error (MSE), percentage depth dose (PDD), and cross beam profile (CBP). Additionally, as the CNN model, 3D-Unet was pre-trained on a virtual dataset.Results With the 50% maximum dose of as the threshold and 3%/3mm as the standard, the central-plane and stereo-mean gamma pass rates of all field reconstruction distributions were over 90%, with MSEs remained below 1%. Besides, the PDD and CBP curves showed MSEs below 1‰ and below 1%, respectively.Conclusions The deep learning-based method for 3D dose reconstruction using scintillation light contributes to enhanced verification of instantaneous 3D relative dose based on plastic scintillation detectors.
HTML  查看全文  查看/发表评论  下载PDF阅读器
关闭