School of Electrical Engineering and Automation, Anhui University, Hefei, People's Republic of China. These authors have contributed equally to this work.
Phys Med Biol. 2020 Oct 21;65(20):205013. doi: 10.1088/1361-6560/aba87b.
This work aims to develop a voxel-level dose prediction framework by integrating distance information between PTV and OARs, as well as image information, into a densely-connected network (DCNN). Firstly, a four-channel feature map, consisting of a PTV image, an OAR image, a CT image, and a distance image, is constructed. A densely connected neural network is then built and trained for voxel-level dose prediction. Considering that the shape and size of OARs are highly inconsistent, a dilated convolution is employed to capture features from multiple scales. Finally, the proposed network is evaluated with five-fold cross-validation, based on ninety-eight clinically approved treatment plans. The voxel-level mean absolute error(MAE ) of DCNN was 2.1% for PTV, 4.6% for left lung, 4.0% for right lung, 5.1% for heart, 6.0% for spinal cord, and 3.4% for body, which outperforms conventional U-Net, Resnet-antiResnet, U-Resnet-D by 0.1-0.8%. This result shows that with the introduction of a distance image and DCNN model, the accuracy of predicted dose distribution could be significantly improved. This approach offers a new dose prediction tool to support quality assurance and the automation of treatment planning in esophageal radiotherapy.
本研究旨在通过将 PTV 与 OAR 之间的距离信息以及图像信息整合到一个密集连接网络（DCNN）中，开发一种体素级剂量预测框架。首先，构建了一个由 PTV 图像、OAR 图像、CT 图像和距离图像组成的四通道特征图。然后，构建并训练一个密集连接神经网络，用于体素级剂量预测。考虑到 OAR 的形状和大小高度不一致，采用扩张卷积从多个尺度捕获特征。最后，基于 98 个临床批准的治疗计划，通过五折交叉验证评估所提出的网络。DCNN 在 PTV、左肺、右肺、心脏、脊髓和身体的体素级平均绝对误差（MAE）分别为 2.1%、4.6%、4.0%、5.1%、6.0%和 3.4%，优于传统的 U-Net、Resnet-antiResnet 和 U-Resnet-D 分别为 0.1-0.8%。该结果表明，通过引入距离图像和 DCNN 模型，可以显著提高预测剂量分布的准确性。该方法为食管放疗的质量保证和治疗计划自动化提供了一种新的剂量预测工具。
