Automated deep learning-based segmentation of COVID-19 lesions from chest computed tomography images

2022
journal article
article
8
dc.abstract.enPurpose: The novel coronavirus COVID-19, which spread globally in late December 2019, is a global health crisis. Chest computed tomography (CT) has played a pivotal role in providing useful information for clinicians to detect COVID-19. However, segmenting COVID-19-infected regions from chest CT results is challenging. Therefore, it is desirable to develop an efficient tool for automated segmentation of COVID-19 lesions using chest CT. Hence, we aimed to propose 2D deep-learning algorithms to automatically segment COVID-19-infected regions from chest CT slices and evaluate their performance. Material and methods: Herein, 3 known deep learning networks: U-Net, U-Net++, and Res-Unet, were trained from scratch for automated segmenting of COVID-19 lesions using chest CT images. The dataset consists of 20 labelled COVID-19 chest CT volumes. A total of 2112 images were used. The dataset was split into 80% for training and validation and 20% for testing the proposed models. Segmentation performance was assessed using Dice similarity coefficient, average symmetric surface distance (ASSD), mean absolute error (MAE), sensitivity, specificity, and precision. Results: All proposed models achieved good performance for COVID-19 lesion segmentation. Compared with Res-Unet, the U-Net and U-Net++ models provided better results, with a mean Dice value of 85.0%. Compared with all models, U-Net gained the highest segmentation performance, with 86.0% sensitivity and 2.22 mm ASSD. The U-Net model obtained 1%, 2%, and 0.66 mm improvement over the Res-Unet model in the Dice, sensitivity, and ASSD, respectively. Compared with Res-Unet, U-Net++ achieved 1%, 2%, 0.1 mm, and 0.23 mm improvement in the Dice, sensitivity, ASSD, and MAE, respectively. Conclusions: Our data indicated that the proposed models achieve an average Dice value greater than 84.0%. Two-dimensional deep learning models were able to accurately segment COVID-19 lesions from chest CT images, assisting the radiologists in faster screening and quantification of the lesion regions for further treatment. Nevertheless, further studies will be required to evaluate the clinical performance and robustness of the proposed models for COVID-19 semantic segmentation.pl
dc.contributor.authorSalehi, Mohammadpl
dc.contributor.authorArdekani, Mahdieh Afkhamipl
dc.contributor.authorTaramsari, Alireza Basharipl
dc.contributor.authorGhaffari, Hamedpl
dc.contributor.authorHaghparast, Mohammadpl
dc.date.accessioned2023-04-05T10:08:56Z
dc.date.available2023-04-05T10:08:56Z
dc.date.issued2022pl
dc.date.openaccess0
dc.description.accesstimew momencie opublikowania
dc.description.additionalBibliogr. s. e485-e486pl
dc.description.physicale478-e486pl
dc.description.versionostateczna wersja wydawcy
dc.description.volume87pl
dc.identifier.doi10.5114/pjr.2022.119027pl
dc.identifier.eissn1899-0967pl
dc.identifier.issn1733-134Xpl
dc.identifier.urihttps://ruj.uj.edu.pl/xmlui/handle/item/309938
dc.languageengpl
dc.language.containerengpl
dc.rightsUdzielam licencji. Uznanie autorstwa - Użycie niekomercyjne - Bez utworów zależnych 4.0 Międzynarodowa*
dc.rights.licenceCC-BY-NC-ND
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/legalcode.pl*
dc.share.typeotwarte repozytorium
dc.subject.endeep learningpl
dc.subject.enimage segmentationpl
dc.subject.eninfection segmentationpl
dc.subject.encomputed tomographypl
dc.subject.enCOVID-19pl
dc.subtypeArticlepl
dc.titleAutomated deep learning-based segmentation of COVID-19 lesions from chest computed tomography imagespl
dc.title.journalPolish Journal of Radiologypl
dc.typeJournalArticlepl
dspace.entity.typePublication
dc.abstract.enpl
Purpose: The novel coronavirus COVID-19, which spread globally in late December 2019, is a global health crisis. Chest computed tomography (CT) has played a pivotal role in providing useful information for clinicians to detect COVID-19. However, segmenting COVID-19-infected regions from chest CT results is challenging. Therefore, it is desirable to develop an efficient tool for automated segmentation of COVID-19 lesions using chest CT. Hence, we aimed to propose 2D deep-learning algorithms to automatically segment COVID-19-infected regions from chest CT slices and evaluate their performance. Material and methods: Herein, 3 known deep learning networks: U-Net, U-Net++, and Res-Unet, were trained from scratch for automated segmenting of COVID-19 lesions using chest CT images. The dataset consists of 20 labelled COVID-19 chest CT volumes. A total of 2112 images were used. The dataset was split into 80% for training and validation and 20% for testing the proposed models. Segmentation performance was assessed using Dice similarity coefficient, average symmetric surface distance (ASSD), mean absolute error (MAE), sensitivity, specificity, and precision. Results: All proposed models achieved good performance for COVID-19 lesion segmentation. Compared with Res-Unet, the U-Net and U-Net++ models provided better results, with a mean Dice value of 85.0%. Compared with all models, U-Net gained the highest segmentation performance, with 86.0% sensitivity and 2.22 mm ASSD. The U-Net model obtained 1%, 2%, and 0.66 mm improvement over the Res-Unet model in the Dice, sensitivity, and ASSD, respectively. Compared with Res-Unet, U-Net++ achieved 1%, 2%, 0.1 mm, and 0.23 mm improvement in the Dice, sensitivity, ASSD, and MAE, respectively. Conclusions: Our data indicated that the proposed models achieve an average Dice value greater than 84.0%. Two-dimensional deep learning models were able to accurately segment COVID-19 lesions from chest CT images, assisting the radiologists in faster screening and quantification of the lesion regions for further treatment. Nevertheless, further studies will be required to evaluate the clinical performance and robustness of the proposed models for COVID-19 semantic segmentation.
dc.contributor.authorpl
Salehi, Mohammad
dc.contributor.authorpl
Ardekani, Mahdieh Afkhami
dc.contributor.authorpl
Taramsari, Alireza Bashari
dc.contributor.authorpl
Ghaffari, Hamed
dc.contributor.authorpl
Haghparast, Mohammad
dc.date.accessioned
2023-04-05T10:08:56Z
dc.date.available
2023-04-05T10:08:56Z
dc.date.issuedpl
2022
dc.date.openaccess
0
dc.description.accesstime
w momencie opublikowania
dc.description.additionalpl
Bibliogr. s. e485-e486
dc.description.physicalpl
e478-e486
dc.description.version
ostateczna wersja wydawcy
dc.description.volumepl
87
dc.identifier.doipl
10.5114/pjr.2022.119027
dc.identifier.eissnpl
1899-0967
dc.identifier.issnpl
1733-134X
dc.identifier.uri
https://ruj.uj.edu.pl/xmlui/handle/item/309938
dc.languagepl
eng
dc.language.containerpl
eng
dc.rights*
Udzielam licencji. Uznanie autorstwa - Użycie niekomercyjne - Bez utworów zależnych 4.0 Międzynarodowa
dc.rights.licence
CC-BY-NC-ND
dc.rights.uri*
http://creativecommons.org/licenses/by-nc-nd/4.0/legalcode.pl
dc.share.type
otwarte repozytorium
dc.subject.enpl
deep learning
dc.subject.enpl
image segmentation
dc.subject.enpl
infection segmentation
dc.subject.enpl
computed tomography
dc.subject.enpl
COVID-19
dc.subtypepl
Article
dc.titlepl
Automated deep learning-based segmentation of COVID-19 lesions from chest computed tomography images
dc.title.journalpl
Polish Journal of Radiology
dc.typepl
JournalArticle
dspace.entity.type
Publication
Affiliations

* The migration of download and view statistics prior to the date of April 8, 2024 is in progress.

Views
2
Views per month
Views per city
San Jose
1
Downloads
salehi_et-al_automated_deep_learning-based_segmentation_of_covid-19_2022.pdf
14