Cargando…

Dense GAN and multi-layer attention based lesion segmentation method for COVID-19 CT images

As the COVID-19 virus spreads around the world, testing and screening of patients have become a headache for governments. With the accumulation of clinical diagnostic data, the imaging big data features of COVID-19 are gradually clear, and CT imaging diagnosis results become more important. To obtai...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhang, Ju, Yu, Lunduan, Chen, Decheng, Pan, Weidong, Shi, Chao, Niu, Yan, Yao, Xinwei, Xu, Xiaobin, Cheng, Yun
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Published by Elsevier Ltd. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8220920/
https://www.ncbi.nlm.nih.gov/pubmed/34178095
http://dx.doi.org/10.1016/j.bspc.2021.102901
_version_ 1783711237358485504
author Zhang, Ju
Yu, Lunduan
Chen, Decheng
Pan, Weidong
Shi, Chao
Niu, Yan
Yao, Xinwei
Xu, Xiaobin
Cheng, Yun
author_facet Zhang, Ju
Yu, Lunduan
Chen, Decheng
Pan, Weidong
Shi, Chao
Niu, Yan
Yao, Xinwei
Xu, Xiaobin
Cheng, Yun
author_sort Zhang, Ju
collection PubMed
description As the COVID-19 virus spreads around the world, testing and screening of patients have become a headache for governments. With the accumulation of clinical diagnostic data, the imaging big data features of COVID-19 are gradually clear, and CT imaging diagnosis results become more important. To obtain clear lesion information from the CT images of patients' lungs is helpful for doctors to adopt effective medical methods, and at the same time, is helpful to screen the patients with real infection. Deep learning image segmentation is widely used in the field of medical image segmentation. However, there are some challenges in using deep learning to segment the lung lesions of COVID-19 patients. Since image segmentation requires the labeling of lesion information on a pixel by pixel basis, most professional radiologists need to screen and diagnose patients on the front line, and they do not have enough energy to label a large amount of image data. In this paper, an improved Dense GAN to expand data set is developed, and a multi-layer attention mechanism method, combined with U-Net's COVID-19 pulmonary CT image segmentation, is proposed. The experimental results showed that the segmentation method proposed in this paper improved the segmentation accuracy of COVID-19 pulmonary medical CT image by comparing with other image segmentation methods.
format Online
Article
Text
id pubmed-8220920
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Published by Elsevier Ltd.
record_format MEDLINE/PubMed
spelling pubmed-82209202021-06-23 Dense GAN and multi-layer attention based lesion segmentation method for COVID-19 CT images Zhang, Ju Yu, Lunduan Chen, Decheng Pan, Weidong Shi, Chao Niu, Yan Yao, Xinwei Xu, Xiaobin Cheng, Yun Biomed Signal Process Control Article As the COVID-19 virus spreads around the world, testing and screening of patients have become a headache for governments. With the accumulation of clinical diagnostic data, the imaging big data features of COVID-19 are gradually clear, and CT imaging diagnosis results become more important. To obtain clear lesion information from the CT images of patients' lungs is helpful for doctors to adopt effective medical methods, and at the same time, is helpful to screen the patients with real infection. Deep learning image segmentation is widely used in the field of medical image segmentation. However, there are some challenges in using deep learning to segment the lung lesions of COVID-19 patients. Since image segmentation requires the labeling of lesion information on a pixel by pixel basis, most professional radiologists need to screen and diagnose patients on the front line, and they do not have enough energy to label a large amount of image data. In this paper, an improved Dense GAN to expand data set is developed, and a multi-layer attention mechanism method, combined with U-Net's COVID-19 pulmonary CT image segmentation, is proposed. The experimental results showed that the segmentation method proposed in this paper improved the segmentation accuracy of COVID-19 pulmonary medical CT image by comparing with other image segmentation methods. Published by Elsevier Ltd. 2021-08 2021-06-23 /pmc/articles/PMC8220920/ /pubmed/34178095 http://dx.doi.org/10.1016/j.bspc.2021.102901 Text en © 2021 Published by Elsevier Ltd. Since January 2020 Elsevier has created a COVID-19 resource centre with free information in English and Mandarin on the novel coronavirus COVID-19. The COVID-19 resource centre is hosted on Elsevier Connect, the company's public news and information website. Elsevier hereby grants permission to make all its COVID-19-related research that is available on the COVID-19 resource centre - including this research content - immediately available in PubMed Central and other publicly funded repositories, such as the WHO COVID database with rights for unrestricted research re-use and analyses in any form or by any means with acknowledgement of the original source. These permissions are granted for free by Elsevier for as long as the COVID-19 resource centre remains active.
spellingShingle Article
Zhang, Ju
Yu, Lunduan
Chen, Decheng
Pan, Weidong
Shi, Chao
Niu, Yan
Yao, Xinwei
Xu, Xiaobin
Cheng, Yun
Dense GAN and multi-layer attention based lesion segmentation method for COVID-19 CT images
title Dense GAN and multi-layer attention based lesion segmentation method for COVID-19 CT images
title_full Dense GAN and multi-layer attention based lesion segmentation method for COVID-19 CT images
title_fullStr Dense GAN and multi-layer attention based lesion segmentation method for COVID-19 CT images
title_full_unstemmed Dense GAN and multi-layer attention based lesion segmentation method for COVID-19 CT images
title_short Dense GAN and multi-layer attention based lesion segmentation method for COVID-19 CT images
title_sort dense gan and multi-layer attention based lesion segmentation method for covid-19 ct images
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8220920/
https://www.ncbi.nlm.nih.gov/pubmed/34178095
http://dx.doi.org/10.1016/j.bspc.2021.102901
work_keys_str_mv AT zhangju denseganandmultilayerattentionbasedlesionsegmentationmethodforcovid19ctimages
AT yulunduan denseganandmultilayerattentionbasedlesionsegmentationmethodforcovid19ctimages
AT chendecheng denseganandmultilayerattentionbasedlesionsegmentationmethodforcovid19ctimages
AT panweidong denseganandmultilayerattentionbasedlesionsegmentationmethodforcovid19ctimages
AT shichao denseganandmultilayerattentionbasedlesionsegmentationmethodforcovid19ctimages
AT niuyan denseganandmultilayerattentionbasedlesionsegmentationmethodforcovid19ctimages
AT yaoxinwei denseganandmultilayerattentionbasedlesionsegmentationmethodforcovid19ctimages
AT xuxiaobin denseganandmultilayerattentionbasedlesionsegmentationmethodforcovid19ctimages
AT chengyun denseganandmultilayerattentionbasedlesionsegmentationmethodforcovid19ctimages