Chen Xinyuan, Zhu Ji, Yang Bining, Chen Deqi, Men Kuo, Dai Jianrong
National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China.
National Cancer Center/National Clinical Research Center for Cancer/Hebei Cancer Hospital, Chinese Academy of Medical Sciences, Langfang, China.
Front Oncol. 2023 Feb 28;13:1041769. doi: 10.3389/fonc.2023.1041769. eCollection 2023.
Deep-learning effectively predicts dose distributions in knowledge-based radiotherapy planning. Using anatomical information that includes a structure map and computed tomography (CT) data as input has been proven to work well. The minimum distance from each voxel in normal structures to planning target volume (DPTV) closely affects each voxel's dose. In this study, we combined DPTV and anatomical information as input for a deep-learning-based dose-prediction network to improve performance.
One hundred patients who underwent volumetric-modulated arc therapy for nasopharyngeal cancer were selected in this study. The prediction model based on a residual network had DPTV maps, structure maps, and CT as inputs and the corresponding dose distribution maps as outputs. The performances of the combined distance and anatomical information (COM) model and the traditional anatomical (ANAT) model with two-channel inputs (structure maps and CT) were compared. A 10-fold cross validation was performed to separately train and test the COM and ANAT models. The voxel-based mean error (ME), mean absolute error (MAE), dosimetric parameters, and dice similarity coefficient (DSC) of isodose volumes were used for modeling evaluation.
The mean MAE of the body volume of the COM model were 4.89 ± 1.35%, highly significantly lower than those for the ANAT model of 5.07 ± 1.37% (0.001). The ME values of the body for the 2-type models were similar (0.05). The mean DSC values of the isodose volumes in the range of 60 Gy were all better in the COM model (<0.05), and there were highly significant differences between 10 Gy and 55 Gy (<0.001). For most organs at risk, the ME, MAE, and dosimetric parameters predicted by both models were concurrent with the ground truth values except the MAE values of the pituitary and optic chiasm in the ANAT model and the average mean dose of the right parotid in the ANAT model.
The COM model outperformed the ANAT model and could improve automated planning with statistically highly significant differences.
深度学习能有效预测基于知识的放射治疗计划中的剂量分布。已证明将包括结构图谱和计算机断层扫描（CT）数据在内的解剖学信息用作输入效果良好。正常结构中每个体素到计划靶体积（DPTV）的最小距离密切影响每个体素的剂量。在本研究中，我们将DPTV和解剖学信息结合作为基于深度学习的剂量预测网络的输入，以提高性能。
本研究选取了100例行鼻咽癌容积调强弧形放疗的患者。基于残差网络的预测模型以DPTV图谱、结构图谱和CT作为输入，以相应的剂量分布图作为输出。比较了具有双通道输入（结构图谱和CT）的组合距离与解剖学信息（COM）模型和传统解剖学（ANAT）模型的性能。进行10折交叉验证以分别训练和测试COM模型和ANAT模型。基于体素的平均误差（ME）、平均绝对误差（MAE）、剂量学参数以及等剂量体积的骰子相似系数（DSC）用于模型评估。
COM模型身体体积的平均MAE为4.89±1.35%，显著低于ANAT模型的5.07±1.37%（P<0.001）。两种模型身体的ME值相似（0.05）。COM模型中60 Gy范围内等剂量体积的平均DSC值均更好（P<0.05），且在10 Gy和55 Gy之间存在高度显著差异（P<0.001）。对于大多数危及器官，除ANAT模型中垂体和视交叉的MAE值以及ANAT模型中右侧腮腺的平均平均剂量外，两种模型预测的ME、MAE和剂量学参数均与真实值一致。
COM模型优于ANAT模型，且能在统计学上以高度显著差异改善自动计划。
