Department of Radiation Oncology, Shanghai Chest Hospital, Shanghai Jiao Tong University, Shanghai, China.
School of Physics and Technology, University of Wuhan, Wuhan, China.
Br J Radiol. 2021 Oct 1;94(1126):20210038. doi: 10.1259/bjr.20210038. Epub 2021 Aug 4.
A stable and accurate automatic tumor delineation method has been developed to facilitate the intelligent design of lung cancer radiotherapy process. The purpose of this paper is to introduce an automatic tumor segmentation network for lung cancer on CT images based on deep learning.
In this paper, a hybrid convolution neural network (CNN) combining 2D CNN and 3D CNN was implemented for the automatic lung tumor delineation using CT images. 3D CNN used V-Net model for the extraction of tumor context information from CT sequence images. 2D CNN used an encoder-decoder structure based on dense connection scheme, which could expand information flow and promote feature propagation. Next, 2D features and 3D features were fused through a hybrid module. Meanwhile, the hybrid CNN was compared with the individual 3D CNN and 2D CNN, and three evaluation metrics, Dice, Jaccard and Hausdorff distance (HD), were used for quantitative evaluation. The relationship between the segmentation performance of hybrid network and the GTV volume size was also explored.
The newly introduced hybrid CNN was trained and tested on a dataset of 260 cases, and could achieve a median value of 0.73, with mean and stand deviation of 0.72 ± 0.10 for the Dice metric, 0.58 ± 0.13 and 21.73 ± 13.30 mm for the Jaccard and HD metrics, respectively. The hybrid network significantly outperformed the individual 3D CNN and 2D CNN in the three examined evaluation metrics ( < 0.001). A larger GTV present a higher value for the Dice metric, but its delineation at the tumor boundary is unstable.
The implemented hybrid CNN was able to achieve good lung tumor segmentation performance on CT images.
The hybrid CNN has valuable prospect with the ability to segment lung tumor.
开发了一种稳定、准确的自动肿瘤勾画方法，以促进肺癌放疗过程的智能化设计。本文旨在介绍一种基于深度学习的 CT 图像肺癌自动肿瘤分割网络。
本文采用二维卷积神经网络（2D CNN）和三维卷积神经网络（3D CNN）相结合的混合卷积神经网络（CNN），对 CT 图像进行自动肺肿瘤勾画。3D CNN 使用 V-Net 模型从 CT 序列图像中提取肿瘤上下文信息。2D CNN 使用基于密集连接方案的编码器-解码器结构，可以扩展信息流，促进特征传播。然后，通过混合模块融合 2D 特征和 3D 特征。同时，将混合 CNN 与单独的 3D CNN 和 2D CNN 进行比较，并使用三个评估指标（Dice、Jaccard 和 Hausdorff 距离（HD））进行定量评估。还探讨了混合网络的分割性能与 GTV 体积大小之间的关系。
新引入的混合 CNN 在 260 例数据集上进行了训练和测试，Dice 指标的中位数为 0.73，平均值和标准差分别为 0.72±0.10；Jaccard 和 HD 指标的平均值和标准差分别为 0.58±0.13 和 21.73±13.30mm。混合网络在三个评估指标上均显著优于单独的 3D CNN 和 2D CNN（<0.001）。较大的 GTV 会使 Dice 指标的值更高，但肿瘤边界的勾画不稳定。
所实现的混合 CNN 能够在 CT 图像上实现良好的肺肿瘤分割性能。
混合 CNN 具有有价值的前景，能够分割肺肿瘤。
