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...
Autores principales: | , , , , , , |
---|---|
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 |