南方医科大学学报

南方医科大学学报 ›› 2023, Vol. 43 ›› Issue (6): 1010-1016.doi: 10.12122/j.issn.1673-4254.2023.06.17

• • 上一篇    下一篇

头颈癌放疗计划剂量分布的预测方法：基于深度学习的算法

滕 琳，王 斌，冯前进   

  1. 南方医科大学生物医学工程学院，广东省医学图像处理重点实验室，广东 广州 510515；上海科技大学生物医学工程学院，上海 201220
  • 出版日期:2023-06-20 发布日期:2023-07-06

Deep learning-based dose prediction in radiotherapy planning for head and neck cancer

TENG Lin, WANG Bin, FENG Qianjin   

  1. School of Biomedical Engineering, Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, Guangzhou 510515, China; School of Biomedical Engineering, ShanghaiTech University, Shanghai 201220, China
  • Online:2023-06-20 Published:2023-07-06

RichHTML

16

PDF

648

摘要： 目的 研究一种基于深度学习的算法，实现头颈癌放疗计划剂量分布的自动预测。方法 本文提出一种射线束剂量肢解学习（BDDL）方法，以级联网络作为基本方法，通过肿瘤分割掩膜PTV和预定义的射线束角度等信息，拟合射线束的传送方式（“射线束分割掩膜”）作为卷积神经网络的输入，将预测全局空间剂量分布肢解为多个沿着射线束方向的子剂量分布图。此过程可将一个困难任务肢解为多个简单的子任务，使模型更关注于局部细节特征的提取。通过射线束投票机制将多个子剂量分布融合为一个全局空间剂量分布。另外，引入感兴趣区域ROIs内剂量分布特征和剂量边界图作为网络学习的约束条件，使网络更加关注ROIs和剂量边界区域特征的提取。利用OpenKBP-2020挑战公开的头颈癌放疗计划数据集，获得BDDL方法在剂量分布预测的精确性，并进行消融实验分析。结果 本研究提出的方法在量化指标Dose score和DVH score分别取得2.166和1.178（P<0.05），预测精度优于目前最先进方法。与挑战第1名方法相比，本文方法使Dose score和DVH score分别提升26.3%和30%。消融实验结果显示BDDL方法各组成部分的有效性。结论 本研究提出的BDDL方法利用了射线束的传送方式和ROIs内剂量分布等先验信息建立剂量预测模型，相比于现有方法是可解释的和可靠的，有望将其应用于临床放疗中。

关键词: 深度学习, 放射治疗计划, 头颈癌, 射线束剂量肢解学习, 剂量体积直方图

Abstract: Objective To propose an deep learning-based algorithm for automatic prediction of dose distribution in radiotherapy planning for head and neck cancer. Methods We propose a novel beam dose decomposition learning (BDDL) method designed on a cascade network. The delivery matter of beam through the planning target volume (PTV) was fitted with the pre-defined beam angles, which served as an input to the convolution neural network (CNN). The output of the network was decomposed into multiple sub- fractions of dose distribution along the beam directions to carry out a complex task by performing multiple simpler sub-tasks, thus allowing the model more focused on extracting the local features. The sub-fractions of dose distribution map were merged into a distribution map using the proposed multi-voting mechanism. We also introduced dose distribution features of the regions-of-interest (ROIs) and boundary map as the loss function during the training phase to serve as constraining factors of the network when extracting features of the ROIs and areas of dose boundary. Public datasets of radiotherapy planning for head and neck cancer were used for obtaining the accuracy of dose distribution of the BDDL method and for implementing the ablation study of the proposed method. Results The BDDL method achieved a Dose score of 2.166 and a DVH score of 1.178 (P<0.05), demonstrating its superior prediction accuracy to that of current state-of-the-art (SOTA) methods. Compared with the C3D method, which was in the first place in OpenKBP-2020 Challenge, the BDDL method improved the Dose score and DVH score by 26.3% and 30% , respectively. The results of the ablation study also demonstrated the effectiveness of each key component of the BDDL method. Conclusion The BDDL method utilizes the prior knowledge of the delivery matter of beam and dose distribution in the ROIs to establish a dose prediction model. Compared with the existing methods, the proposed method is interpretable and reliable and can be potentially applied in clinical radiotherapy.

Key words: deep learning, radiotherapy planning, head and neck cancer, beam- wise dose decomposition learning, dose-volume histogram