文献类型：期刊文献

中文题名：基于WU-Net网络的肺结节图像分割算法

英文题名：Improved lung nodules segmentation algorithm based on WU-Net

作者：张宇杰[1];叶西宁[1]

机构：[1]华东理工大学信息科学与工程学院,上海200237

年份：2022

卷号：39

期号：3

起止页码：895

中文期刊名：计算机应用研究

外文期刊名：Application Research of Computers

收录：CSTPCD;;北大核心:【北大核心2020】；CSCD:【CSCD_E2021_2022】；

基金：国家自然科学基金资助项目(60974066)。

语种：中文

中文关键词：肺结节分割;深度卷积神经网络;WU-Net;多尺度融合;图像分割

外文关键词：lung nodule segmentation;deep neural convolution network;WU-Net;multi-scale fusion;image segmentation

摘要：深度卷积神经网络在医学图像分割领域运用广泛,目前的网络改进普遍是引入多尺度融合结构,增加了模型的复杂度,在提升精度的同时降低了训练效率。针对上述问题,提出一种新型的WU-Net肺结节图像分割方法。该方法对U-Net网络进行改进,在原下采样编码通路引入改进的残余连接模块,同时利用新提出的dep模块改进的信息通路完成特征提取和特征融合。实验利用LUNA16的数据集对WU-Net和其他模型进行训练和验证,在以结节为尺度的实验中,Dice系数和交并比分别能达到96.72%、91.78%;在引入10%的负样本后,F;值达到了92.41%,相比UNet3+提高了1.23%;在以肺实质为尺度的实验中,Dice系数和交并比分别达到了83.33%、66.79%,相比RU-Net分别提升了1.35%、2.53%。相比其他模型,WU-Net模型的分割速度最快,比U-Net提升了39.6%。结果显示,WU-Net提升肺结节分割效果的同时加快了模型的训练速度。
Deep convolutional neural network is widely used in the field of medical image segmentation.In recent years, multi-scale fusion structure is used to improve segmentation network, which often increases the complexity of the model and reduces the training efficiency while improving the accuracy.To solve these problems, this paper proposed a novel segmentation algorithm for WU-Net pulmonary nodules.It improved the U-Net by introducing an improved residual connection module into the original down-sampling coding channel and mean while using the information channel improved by the new dep module to complete feature extraction and feature fusion.In the experiment, it used LUNA16 dataset to train and verify the model.Meanwhile, comparative experiments used some newly segmentation models.In the experiment with scale of nodules, the Dice coefficient and IoU of proposed model can reach 96.72% and 91.78% respectively.F;-score can reach 92.41% after adding 10% negative samples, which is 1.23% higher than UNet3+.In the experiment with scale of lung parenchyma, the Dice coefficient and IoU of proposed model can reach 83.33% and 66.79% respectively, which is 1.35% and 2.53% higher than RU-Net.The training efficiency of WU-Net is the highest, which is 39.6% higher than U-Net spend.The result shows that WU-Net has improved segmentation effects and training efficiency of model as well.