Stepwise deep neural network (stepwise-net) for head and neck auto-segmentation on CT images
Stepwise deep neural network (stepwise-net) for head and neck auto-segmentation on CT images
复制标题
基于逐步深度神经网络（Stepwise -net）的CT图像头颈部自动分割
DOI：
10.1016/j.compbiomed.2022.105295
复制
发表时间：
2022-02-12
影响因子：
7.7
通讯作者：
Nagata, Yasushi
中科院分区：
文献类型：
--
作者：
Kawahara, Daisuke;Tsuneda, Masato;Nagata, Yasushi
目的：提出一种基于逐步深度神经网络（stepwise-net）的头颈部肿瘤CT图像自动分割模型。材料与方法：对3D CT图像中头颈部区域的6个正常组织结构：脑干、视神经、腮腺（左、右）、下颌下腺（左、右）进行深度学习分割。在传统卷积神经网络（CNN）的基础上，提出了逐步神经网络（stepwise-network）。该逐步网络基于三维FCN。我们在逐步网络中设计了两个网络。一是利用低分辨率图像识别目标区域进行分割。然后，对目标区域进行裁剪，用于输入图像的分割预测。这些与临床使用的基于地图集的分割进行比较。结果：在所有危险器官结构中，阶梯网的dsc均显著高于基于图谱的方法。同样，对于所有危险器官结构，阶梯网络的JSCs明显高于基于图谱的方法。对于所有器官危险结构，Hausdorff距离（HD）明显小于基于图谱的方法。阶梯式网络与u型网络的比较表明，阶梯式网络的DSC和JSC高于传统u型网络，HD小于传统u型网络。结论：逐步网络的分割效果优于传统的基于u -net和基于图谱的分割。我们提出的模型是一个潜在的有价值的方法，以提高头颈部放射治疗计划的效率。
Objective: The current study aims to propose the auto-segmentation model on CT images of head and neck cancer using a stepwise deep neural network (stepwise-net).Material and methods: Six normal tissue structures in the head and neck region of 3D CT images: Brainstem, optic nerve, parotid glands (left and right), and submandibular glands (left and right) were segmented with deep learning. In addition to a conventional convolutional neural network (CNN) on U-net, a stepwise neural network (stepwise-network) was developed. The stepwise-network was based on 3D FCN. We designed two networks in the stepwise-network. One is identifying the target region for the segmentation with the low-resolution images. Then, the target region is cropped, which used for the input image for the prediction of the segmentation. These were compared with a clinical used atlas-based segmentation.Results: The DSCs of the stepwise-net was significantly higher than the atlas-based method for all organ at risk structures. Similarly, the JSCs of the stepwise-net was significantly higher than the atlas-based methods for all organ at risk structures. The Hausdorff distance (HD) was significantly smaller than the atlas-based method for all organ at-risk structures. For the comparison of the stepwise-net and U-net, the stepwise-net had a higher DSC and JSC and a smaller HD than the conventional U-net.Conclusions: We found that the stepwise-network plays a role is superior to conventional U-net-based and atlas based segmentation. Our proposed model that is a potentially valuable method for improving the efficiency of head and neck radiotherapy treatment planning.