School of Computer Science and Engineering, Hunan University of Science and Technology, Xiangtan, 411100, China.
College of Intelligence Science and Technology, National University of Defense Technology, Changsha, 410073, China.
Artif Intell Med. 2024 Oct;156:102961. doi: 10.1016/j.artmed.2024.102961. Epub 2024 Aug 18.
Dose prediction is a crucial step in automated radiotherapy planning for liver cancer. Several deep learning-based approaches for dose prediction have been proposed to enhance the design efficiency and quality of radiotherapy plan. However, these approaches usually take CT images and contours of organs at risk (OARs) and planning target volume (PTV) as a multi-channel input and is thus difficult to extract sufficient feature information from each input, which results in unsatisfactory dose distribution. In this paper, we propose a novel dose prediction network for liver cancer based on hierarchical feature fusion and interactive attention. A feature extraction module is first constructed to extract multi-scale features from different inputs, and a hierarchical feature fusion module is then built to fuse these multi-scale features hierarchically. A decoder based on attention mechanism is designed to gradually reconstruct the fused features into dose distribution. Additionally, we design an autoencoder network to generate a perceptual loss during training stage, which is used to improve the accuracy of dose prediction. The proposed method is tested on private clinical dataset and obtains HI and CI of 0.31 and 0.87, respectively. The experimental results are better than those by several existing methods, indicating that the dose distribution generated by the proposed method is close to that approved in clinics. The codes are available at https://github.com/hired-ld/FA-Net.
剂量预测是肝癌自动化放射治疗计划的关键步骤。已经提出了几种基于深度学习的剂量预测方法，以提高放射治疗计划的设计效率和质量。然而，这些方法通常将 CT 图像和危及器官（OARs）和计划靶区（PTV）的轮廓作为多通道输入，因此难以从每个输入中提取足够的特征信息，从而导致剂量分布不理想。在本文中，我们提出了一种基于分层特征融合和交互注意力的肝癌新型剂量预测网络。首先构建特征提取模块，从不同的输入中提取多尺度特征，然后构建分层特征融合模块，将这些多尺度特征分层融合。设计了基于注意力机制的解码器，将融合后的特征逐步重构为剂量分布。此外，我们设计了一个自动编码器网络，在训练阶段生成感知损失，用于提高剂量预测的准确性。该方法在私人临床数据集上进行了测试，分别获得了 0.31 和 0.87 的 HI 和 CI。实验结果优于几种现有方法，表明该方法生成的剂量分布接近临床认可的剂量分布。代码可在 https://github.com/hired-ld/FA-Net 获得。
