Cargando…

ADID-UNET—a segmentation model for COVID-19 infection from lung CT scans

Currently, the new coronavirus disease (COVID-19) is one of the biggest health crises threatening the world. Automatic detection from computed tomography (CT) scans is a classic method to detect lung infection, but it faces problems such as high variations in intensity, indistinct edges near lung in...

Descripción completa

Detalles Bibliográficos
Autores principales: Joseph Raj, Alex Noel, Zhu, Haipeng, Khan, Asiya, Zhuang, Zhemin, Yang, Zengbiao, Mahesh, Vijayalakshmi G. V., Karthik, Ganesan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: PeerJ Inc. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7924694/
https://www.ncbi.nlm.nih.gov/pubmed/33816999
http://dx.doi.org/10.7717/peerj-cs.349
_version_ 1783659143111901184
author Joseph Raj, Alex Noel
Zhu, Haipeng
Khan, Asiya
Zhuang, Zhemin
Yang, Zengbiao
Mahesh, Vijayalakshmi G. V.
Karthik, Ganesan
author_facet Joseph Raj, Alex Noel
Zhu, Haipeng
Khan, Asiya
Zhuang, Zhemin
Yang, Zengbiao
Mahesh, Vijayalakshmi G. V.
Karthik, Ganesan
author_sort Joseph Raj, Alex Noel
collection PubMed
description Currently, the new coronavirus disease (COVID-19) is one of the biggest health crises threatening the world. Automatic detection from computed tomography (CT) scans is a classic method to detect lung infection, but it faces problems such as high variations in intensity, indistinct edges near lung infected region and noise due to data acquisition process. Therefore, this article proposes a new COVID-19 pulmonary infection segmentation depth network referred as the Attention Gate-Dense Network- Improved Dilation Convolution-UNET (ADID-UNET). The dense network replaces convolution and maximum pooling function to enhance feature propagation and solves gradient disappearance problem. An improved dilation convolution is used to increase the receptive field of the encoder output to further obtain more edge features from the small infected regions. The integration of attention gate into the model suppresses the background and improves prediction accuracy. The experimental results show that the ADID-UNET model can accurately segment COVID-19 lung infected areas, with performance measures greater than 80% for metrics like Accuracy, Specificity and Dice Coefficient (DC). Further when compared to other state-of-the-art architectures, the proposed model showed excellent segmentation effects with a high DC and F1 score of 0.8031 and 0.82 respectively.
format Online
Article
Text
id pubmed-7924694
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher PeerJ Inc.
record_format MEDLINE/PubMed
spelling pubmed-79246942021-04-02 ADID-UNET—a segmentation model for COVID-19 infection from lung CT scans Joseph Raj, Alex Noel Zhu, Haipeng Khan, Asiya Zhuang, Zhemin Yang, Zengbiao Mahesh, Vijayalakshmi G. V. Karthik, Ganesan PeerJ Comput Sci Human-Computer Interaction Currently, the new coronavirus disease (COVID-19) is one of the biggest health crises threatening the world. Automatic detection from computed tomography (CT) scans is a classic method to detect lung infection, but it faces problems such as high variations in intensity, indistinct edges near lung infected region and noise due to data acquisition process. Therefore, this article proposes a new COVID-19 pulmonary infection segmentation depth network referred as the Attention Gate-Dense Network- Improved Dilation Convolution-UNET (ADID-UNET). The dense network replaces convolution and maximum pooling function to enhance feature propagation and solves gradient disappearance problem. An improved dilation convolution is used to increase the receptive field of the encoder output to further obtain more edge features from the small infected regions. The integration of attention gate into the model suppresses the background and improves prediction accuracy. The experimental results show that the ADID-UNET model can accurately segment COVID-19 lung infected areas, with performance measures greater than 80% for metrics like Accuracy, Specificity and Dice Coefficient (DC). Further when compared to other state-of-the-art architectures, the proposed model showed excellent segmentation effects with a high DC and F1 score of 0.8031 and 0.82 respectively. PeerJ Inc. 2021-01-26 /pmc/articles/PMC7924694/ /pubmed/33816999 http://dx.doi.org/10.7717/peerj-cs.349 Text en © 2021 Joseph Raj et al. https://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ Computer Science) and either DOI or URL of the article must be cited.
spellingShingle Human-Computer Interaction
Joseph Raj, Alex Noel
Zhu, Haipeng
Khan, Asiya
Zhuang, Zhemin
Yang, Zengbiao
Mahesh, Vijayalakshmi G. V.
Karthik, Ganesan
ADID-UNET—a segmentation model for COVID-19 infection from lung CT scans
title ADID-UNET—a segmentation model for COVID-19 infection from lung CT scans
title_full ADID-UNET—a segmentation model for COVID-19 infection from lung CT scans
title_fullStr ADID-UNET—a segmentation model for COVID-19 infection from lung CT scans
title_full_unstemmed ADID-UNET—a segmentation model for COVID-19 infection from lung CT scans
title_short ADID-UNET—a segmentation model for COVID-19 infection from lung CT scans
title_sort adid-unet—a segmentation model for covid-19 infection from lung ct scans
topic Human-Computer Interaction
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7924694/
https://www.ncbi.nlm.nih.gov/pubmed/33816999
http://dx.doi.org/10.7717/peerj-cs.349
work_keys_str_mv AT josephrajalexnoel adidunetasegmentationmodelforcovid19infectionfromlungctscans
AT zhuhaipeng adidunetasegmentationmodelforcovid19infectionfromlungctscans
AT khanasiya adidunetasegmentationmodelforcovid19infectionfromlungctscans
AT zhuangzhemin adidunetasegmentationmodelforcovid19infectionfromlungctscans
AT yangzengbiao adidunetasegmentationmodelforcovid19infectionfromlungctscans
AT maheshvijayalakshmigv adidunetasegmentationmodelforcovid19infectionfromlungctscans
AT karthikganesan adidunetasegmentationmodelforcovid19infectionfromlungctscans