当前位置: X-MOL 学术J. Radiat. Res. Appl. Sci. › 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.)
Application of virtual noncontrast CT generation technology from intravenous enhanced CT based on deep learning in proton radiotherapy
Journal of Radiation Research and Applied Sciences ( IF 1.7 ) Pub Date : 2022-03-18 , DOI: 10.1016/j.jrras.2022.03.003
Jianfeng Sui , Liugang Gao , Haijiao Shang , Chunying Li , Zhengda Lu , Mu He , Tao Lin , Kai Xie , Jiawei Sun , Hui Bi , Xinye Ni

The aim of this study is to generate virtual noncontrast (VNC) computed tomography (CT) from intravenous enhanced CT by using Unet convolutional neural network (CNN). The differences among enhanced, VNC, and noncontrast CT in proton dose calculation were compared. A total of 30 groups of CT images of patients who received enhanced and noncontrast CT were selected. Enhanced and noncontrast CT were registered. Among these patients, 20 groups of the CT images were chosen as the training set. Enhanced CT images were used as the input, and the corresponding noncontrast CT images were used as output to train the Unet neural network. The remaining 10 groups of CT images were chosen as the test set. VNC images were generated by the trained Unet neural network. The same proton radiotherapy plan for esophagus cancer was designed based on three images. Proton dose distributions in enhanced, VNC, and noncontrast CT were calculated. The relative dose differences in enhanced CT with VNC and noncontrast CT were analyzed. The mean absolute error (MAE) of the CT values between enhanced and noncontrast CT was 32.3 ± 2.6 HU. The MAE of the CT values between VNC and noncontrast CT was 6.7 ± 1.3 HU. The mean values of the enhanced CT in the great vessel, heart, lung, liver, and spinal cord were significantly higher than those of noncontrast CT, he differences were 97, 83, 42, 40, and 10 HU, respectively. The mean values of the VNC CT showed no significant difference with noncontrast CT. The differences among enhanced, VNC, and noncontrast CT in terms of the average relative proton dose for clinical target volume (CTV), heart, great vessels, and lung were also investigated. The average relative proton doses of the enhanced CT for these organs were significantly lower than those of noncontrast CT. The largest difference was observed in the great vessel, while the differences in other organs were relatively small. The γ-passing rates of the enhanced and VNC CT were calculated by 2% dose difference and 2 mm distance to agreement. Results showed that the mean γ-passing rate of VNC CT was significantly higher than enhanced CT (p < 0.05). The proton radiotherapy design based on enhanced CT increased the range error, thereby resulting in calculation errors of the proton dose. Therefore, a technology that can be used to generate VNC CT from enhanced CT based on Unet neural network was proposed. The proton dose calculated based on VNC CT images was essentially consistent with that based on noncontrast CT.

中文翻译:

基于深度学习的静脉增强CT虚拟平扫CT生成技术在质子放疗中的应用

本研究的目的是使用 Unet 卷积神经网络 (CNN) 从静脉增强 CT 生成虚拟非造影 (VNC) 计算机断层扫描 (CT)。比较增强、VNC和平扫CT在质子剂量计算方面的差异。共选取30组接受增强和平扫CT患者的CT图像。登记了增强 CT 和平扫 CT。其中,选择20组CT图像作为训练集。以增强CT图像作为输入,相应的非增强CT图像作为输出来训练Unet神经网络。选择其余10组CT图像作为测试集。 VNC 图像由经过训练的 Unet 神经网络生成。基于三幅图像设计了相同的食管癌质子放射治疗计划。计算了增强 CT、VNC 和平扫 CT 中的质子剂量分布。分析了VNC增强CT和平扫CT的相对剂量差异。增强 CT 与平扫 CT 之间的 CT 值的平均绝对误差 (MAE) 为 32.3 ± 2.6 HU。 VNC 和非增强 CT 之间的 CT 值的 MAE 为 6.7 ± 1.3 HU。大血管、心、肺、肝、脊髓增强CT平均值均显着高于平扫CT,差异分别为97、83、42、40、10 HU。 VNC CT 的平均值与非增强 CT 没有显着差异。还研究了增强 CT、VNC 和平扫 CT 在临床靶区 (CTV)、心脏、大血管和肺的平均相对质子剂量方面的差异。这些器官增强CT的平均相对质子剂量显着低于平扫CT。在大血管中观察到最大的差异,而其他器官的差异相对较小。增强CT和VNC CT的γ通过率通过2%剂量差和2 mm一致距离计算。结果显示,VNC CT 的平均 γ 通过率显着高于增强 CT (p < 0.05)。基于增强CT的质子放疗设计增加了射程误差,从而导致质子剂量的计算误差。因此,提出了一种基于Unet神经网络的增强CT生成VNC CT的技术。基于VNC CT图像计算的质子剂量与基于平扫CT计算的质子剂量基本一致。
更新日期:2022-03-18
down
wechat
bug