文献类型：期刊文献

英文题名：A multi-class COVID-19 segmentation network with pyramid attention and edge loss in CT images

作者：Yu, Fuli[1];Zhu, Yu[1];Qin, Xiangxiang[1];Xin, Ying[2];Yang, Dawei[3];Xu, Tao[4]

机构：[1]East China Univ Sci & Technol, Sch Informat Sci & Engn, Shanghai 200237, Peoples R China;[2]Affiliated Hosp Qingdao Univ, Dept Endocrine & Metab Dis, Qingdao 266003, Peoples R China;[3]Fudan Univ, Zhongshan Hosp, Dept Pulm Med, Shanghai 200032, Peoples R China;[4]Affiliated Hosp Qingdao Univ, Dept Pulm & Crit Care Med, Qingdao 266000, Shandong, Peoples R China

年份：2021

卷号：15

期号：11

起止页码：2604

外文期刊名：IET IMAGE PROCESSING

收录：;EI(收录号：20211910321400);WOS:【SCI-EXPANDED(收录号:WOS:000646886100001)】；

基金：Qingdao City Science andTechnology Special Fund No.20-4-1-5-nshr Qingdao West Coast New District Science and Technology Project 2019-59. Shanghai Pujiang Program (20PJ1402400), Science and Technology Commission of Shanghai Municipality (20DZ2261200) and Shanghai Engineer & Technology Research Center of Internet of Things for Respiratory Medicine (20DZ2254400).

语种：英文

外文关键词：Image segmentation - Diagnosis - Computerized tomography - Medical imaging - Image enhancement

摘要：At the end of 2019, a novel coronavirus COVID-19 broke out. Due to its high contagiousness, more than 74 million people have been infected worldwide. Automatic segmentation of the COVID-19 lesion area in CT images is an effective auxiliary medical technology which can quantitatively diagnose and judge the severity of the disease. In this paper, a multi-class COVID-19 CT image segmentation network is proposed, which includes a pyramid attention module to extract multi-scale contextual attention information, and a residual convolution module to improve the discriminative ability of the network. A wavelet edge loss function is also proposed to extract edge features of the lesion area to improve the segmentation accuracy. For the experiment, a dataset of 4369 CT slices is constructed, including three symptoms: ground glass opacities, interstitial infiltrates, and lung consolidation. The dice similarity coefficients of three symptoms of the model achieve 0.7704, 0.7900, 0.8241 respectively. The performance of the proposed network on public dataset COVID-SemiSeg is also evaluated. The results demonstrate that this model outperforms other state-of-the-art methods and can be a powerful tool to assist in the diagnosis of positive infection cases, and promote the development of intelligent technology in the medical field.