基于双注意力3D-UNet的肺结节分割网络模型

为提高计算机辅助诊断系统对大尺寸肺结节分割的完整度以及小尺寸肺结节的分割精度，构建双注意力3D-UNet肺结节分割网络模型。将传统3D-UNet网络中的上采样操作替换为DUpsampling结构，通过最小化特征图的像素点与被压缩标签图像之间的损失，得到更具表达能力的特征图，进而提高网络收敛速度。在此基础上，融入空间注意力模块和通道注意力模块，使单通道与多通道中相似的特征彼此相关，增加特征图的全局相关性以提高分割结果的精度。实验结果表明，与3D-UNet等方法相比，该模型有效提高了肺结节分割的准确率，在公共数据集LIDC-IDRI上的MIoU分数达到89.4%。

Network Model for Lung Nodule Segmentation Based onDouble Attention 3D-UNet

In order to improve the segmentation integrity of large pulmonary nodules and the segmentation accuracy of small pulmonary nodules in computer-aided diagnosis systems,this paper constructs a Double Attention 3 D-UNet(DA3 D-UNet)for lung nodule segmentation.The traditional upsampling operation in the 3 D-UNet network is replaced with the DUpsampling structure. By minimizing the loss between the pixels of the feature map and the compressed label image,a more expressive feature map is obtained,thereby improving the network convergence speed.On this basis,the spatial attention module and the channel attention module are integrated to make the similar features in the single channel and the multi-channel correlated with each other,increase the global correlation of the feature map,and improve the accuracy of the segmentation result.Experimental results show that compared with 3 D-UNet and other methods,this model effectively improves the accuracy of lung nodule segmentation,and its MIoU score on the public data set LIDCIDRI reaches 89.4%.