摘要
肺癌是全球死亡率最高的癌症之一,肺结节作为肺癌早期诊断的重要依据,对其进行精准分割格外重要。为了帮助医生诊断肺部病变,本文提出一种改进的UNet肺结节分割方法。首先,在特征提取部分引入高效通道注意力网络(efficient channel attention for deep convolutional neural networks,EcaNet),提高UNet分割效果,使其具有良好的泛化能力。接着,为了降低模型参数量、提升算法分割性能,提出一种基于深度可分离卷积的特征融合模型,用深度可分离卷积代替传统卷积完成特征融合。然后,针对肺结节图像特点,将基于重叠度损失函数(dice loss)与加权交叉熵(weighted cross entropy,WCE)结合作为新的损失函数。最后,为验证所提算法Eca-UNet的有效性,在LIDC-IDRI肺结节公开数据集上进行评估。结果表明:Eca-UNet算法在DICE相似系数、MIOU上比UNet分割算法分别提高10.47、7.34个百分点;同时在训练速度上提升了10.10%,预测速度提升了11.56%。
Lung cancer is one of the cancers with the highest mortality in the world.As an important basis for early diagnosis of lung cancer,accurate segmentation of pulmonary nodules is particularly important.In order to help doctors diagnose lung lesions,an improved UNet lung nodule segmentation method is proposed.First,Efficient Channel Attention for Deep Convolutional Neural Networks(EcaNet)is introduced in the feature extraction part,which improves the UNet segmentation effect and makes it have good generalization ability.At the same time,in order to reduce the number of parameters of the model and improve the segmentation performance of the algorithm,a feature fusion model of depthwise separable convolution is proposed,which replaces the traditional convolution operation with depthwise separable convolution to complete feature fusion.According to the image characteristics of pulmonary nodules,the Dice Loss and the weighted cross entropy(WCE)are combined as a new loss function.To verify the effectiveness of the proposed algorithm Eca-UNet,our evaluated on the LIDC-IDRI public dataset of lung nodules.The results show that the DICE similarity coefficient and MIOU of the Eca-UNet algorithm are 10.47%and 7.34%higher than that of the UNet segmentation algorithm,respectively.At the same time,the training speed has increased by 10.10%,and the prediction speed has increased by 11.56%.
作者
万黎明
张小乾
刘知贵
宋林
周莹
李理
WAN Liming;ZHANG Xiaoqian;LIU Zhigui;SONG Lin;ZHOU Ying;LI Li(School of Computer Science and Technology,Southwest University of Science and Technology,Mianyang Sichuan 621000,China;School of Information Engineering,Southwest University of Science and Technology,Mianyang Sichuan 621000,China;Department of Radiology,Mianyang Central Hospital,Mianyang Sichuan 621000,China)
出处
《广西师范大学学报（自然科学版）》
CAS
北大核心
2022年第3期66-75,共10页
Journal of Guangxi Normal University:Natural Science Edition
基金
国家自然科学基金(61772272,62102331)。
关键词
图像分割
肺结节CT图像
注意力机制
UNet
残差网络
image segmentation
CT images of pulmonary nodules
attention mechanism
UNet
residual network
