A multi‐class COVID‐19 segmentation network with pyramid attention and edge loss in CT images
Abstract 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 diagnos...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2021-09-01
|
Series: | IET Image Processing |
Subjects: | |
Online Access: | https://doi.org/10.1049/ipr2.12249 |
_version_ | 1811266468723032064 |
---|---|
author | Fuli Yu Yu Zhu Xiangxiang Qin Ying Xin Dawei Yang Tao Xu |
author_facet | Fuli Yu Yu Zhu Xiangxiang Qin Ying Xin Dawei Yang Tao Xu |
author_sort | Fuli Yu |
collection | DOAJ |
description | Abstract 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. |
first_indexed | 2024-04-12T20:43:55Z |
format | Article |
id | doaj.art-74afe5ee31174f70aa4899ae2e969066 |
institution | Directory Open Access Journal |
issn | 1751-9659 1751-9667 |
language | English |
last_indexed | 2024-04-12T20:43:55Z |
publishDate | 2021-09-01 |
publisher | Wiley |
record_format | Article |
series | IET Image Processing |
spelling | doaj.art-74afe5ee31174f70aa4899ae2e9690662022-12-22T03:17:20ZengWileyIET Image Processing1751-96591751-96672021-09-0115112604261310.1049/ipr2.12249A multi‐class COVID‐19 segmentation network with pyramid attention and edge loss in CT imagesFuli Yu0Yu Zhu1Xiangxiang Qin2Ying Xin3Dawei Yang4Tao Xu5School of Information Science and Engineering East China University of Science and Technology Shanghai 200237 People's Republic of ChinaSchool of Information Science and Engineering East China University of Science and Technology Shanghai 200237 People's Republic of ChinaSchool of Information Science and Engineering East China University of Science and Technology Shanghai 200237 People's Republic of ChinaDepartment of Endocrine and Metabolic Diseases The Affiliated Hospital of Qingdao University Qingdao 266003 People's Republic of ChinaDepartment of Pulmonary Medicine Zhongshan Hospital Fudan University Shanghai 200032 People's Republic of ChinaDepartment of Pulmonary and Critical Care Medicine The Affiliated Hospital of Qingdao University Qingdao Shandong 266000 People's Republic of ChinaAbstract 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.https://doi.org/10.1049/ipr2.12249X‐rays and particle beams (medical uses)Patient diagnostic methods and instrumentationOptical, image and video signal processingImage recognitionX‐ray techniques: radiography and computed tomography (biomedical imaging/measurement)Computer vision and image processing techniques |
spellingShingle | Fuli Yu Yu Zhu Xiangxiang Qin Ying Xin Dawei Yang Tao Xu A multi‐class COVID‐19 segmentation network with pyramid attention and edge loss in CT images IET Image Processing X‐rays and particle beams (medical uses) Patient diagnostic methods and instrumentation Optical, image and video signal processing Image recognition X‐ray techniques: radiography and computed tomography (biomedical imaging/measurement) Computer vision and image processing techniques |
title | A multi‐class COVID‐19 segmentation network with pyramid attention and edge loss in CT images |
title_full | A multi‐class COVID‐19 segmentation network with pyramid attention and edge loss in CT images |
title_fullStr | A multi‐class COVID‐19 segmentation network with pyramid attention and edge loss in CT images |
title_full_unstemmed | A multi‐class COVID‐19 segmentation network with pyramid attention and edge loss in CT images |
title_short | A multi‐class COVID‐19 segmentation network with pyramid attention and edge loss in CT images |
title_sort | multi class covid 19 segmentation network with pyramid attention and edge loss in ct images |
topic | X‐rays and particle beams (medical uses) Patient diagnostic methods and instrumentation Optical, image and video signal processing Image recognition X‐ray techniques: radiography and computed tomography (biomedical imaging/measurement) Computer vision and image processing techniques |
url | https://doi.org/10.1049/ipr2.12249 |
work_keys_str_mv | AT fuliyu amulticlasscovid19segmentationnetworkwithpyramidattentionandedgelossinctimages AT yuzhu amulticlasscovid19segmentationnetworkwithpyramidattentionandedgelossinctimages AT xiangxiangqin amulticlasscovid19segmentationnetworkwithpyramidattentionandedgelossinctimages AT yingxin amulticlasscovid19segmentationnetworkwithpyramidattentionandedgelossinctimages AT daweiyang amulticlasscovid19segmentationnetworkwithpyramidattentionandedgelossinctimages AT taoxu amulticlasscovid19segmentationnetworkwithpyramidattentionandedgelossinctimages AT fuliyu multiclasscovid19segmentationnetworkwithpyramidattentionandedgelossinctimages AT yuzhu multiclasscovid19segmentationnetworkwithpyramidattentionandedgelossinctimages AT xiangxiangqin multiclasscovid19segmentationnetworkwithpyramidattentionandedgelossinctimages AT yingxin multiclasscovid19segmentationnetworkwithpyramidattentionandedgelossinctimages AT daweiyang multiclasscovid19segmentationnetworkwithpyramidattentionandedgelossinctimages AT taoxu multiclasscovid19segmentationnetworkwithpyramidattentionandedgelossinctimages |