As one of the cancers with the highest mortality rate in the world,lung cancer is a serious threat to human life.Early detection and early treatment can improve the survival rate of patients.In order to accurately segment the pulmonary nodules in the pulmonary CT images,a CAM U-Net based pulmonary nodules segmentation method was proposed.On the basis of U-Net network,the channel attention module CAM is added to make the features in the network focus on the key useful information,weaken or even eliminate the interference of irrelevant information,so as to improve the performance of the model.Experimental results on the LIDC-IDRI public dataset of pulmonary nodules show that the proposed method can achieve intersection over union,Dice similarity coefficient,precision and recall of 82.04%,89.24%,88.61%and 91.28%,respectively.Compared with other segmentation methods for lung nodules,this algorithm has better segmentation performance.
国家科技期刊平台
NSTL
万方数据
