COVID-19 infection localization and severity grading from chest X-ray images

<p dir="ltr">The immense spread of coronavirus disease 2019 (COVID-19) has left healthcare systems incapable to diagnose and test patients at the required rate. Given the effects of COVID-19 on pulmonary tissues, chest radiographic imaging has become a necessity for screening and mon...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Anas M. Tahir (16870077) (author)
مؤلفون آخرون: Muhammad E.H. Chowdhury (17151154) (author), Amith Khandakar (14151981) (author), Tawsifur Rahman (14150523) (author), Yazan Qiblawey (16904838) (author), Uzair Khurshid (17151157) (author), Serkan Kiranyaz (3762058) (author), Nabil Ibtehaz (16888773) (author), M. Sohel Rahman (12056885) (author), Somaya Al-Maadeed (5178131) (author), Sakib Mahmud (15302404) (author), Maymouna Ezeddin (16891368) (author), Khaled Hameed (17151160) (author), Tahir Hamid (16869921) (author)
منشور في: 2021
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513552561209344
author Anas M. Tahir (16870077)
author2 Muhammad E.H. Chowdhury (17151154)
Amith Khandakar (14151981)
Tawsifur Rahman (14150523)
Yazan Qiblawey (16904838)
Uzair Khurshid (17151157)
Serkan Kiranyaz (3762058)
Nabil Ibtehaz (16888773)
M. Sohel Rahman (12056885)
Somaya Al-Maadeed (5178131)
Sakib Mahmud (15302404)
Maymouna Ezeddin (16891368)
Khaled Hameed (17151160)
Tahir Hamid (16869921)
author2_role author
author
author
author
author
author
author
author
author
author
author
author
author
author_facet Anas M. Tahir (16870077)
Muhammad E.H. Chowdhury (17151154)
Amith Khandakar (14151981)
Tawsifur Rahman (14150523)
Yazan Qiblawey (16904838)
Uzair Khurshid (17151157)
Serkan Kiranyaz (3762058)
Nabil Ibtehaz (16888773)
M. Sohel Rahman (12056885)
Somaya Al-Maadeed (5178131)
Sakib Mahmud (15302404)
Maymouna Ezeddin (16891368)
Khaled Hameed (17151160)
Tahir Hamid (16869921)
author_role author
dc.creator.none.fl_str_mv Anas M. Tahir (16870077)
Muhammad E.H. Chowdhury (17151154)
Amith Khandakar (14151981)
Tawsifur Rahman (14150523)
Yazan Qiblawey (16904838)
Uzair Khurshid (17151157)
Serkan Kiranyaz (3762058)
Nabil Ibtehaz (16888773)
M. Sohel Rahman (12056885)
Somaya Al-Maadeed (5178131)
Sakib Mahmud (15302404)
Maymouna Ezeddin (16891368)
Khaled Hameed (17151160)
Tahir Hamid (16869921)
dc.date.none.fl_str_mv 2021-12-01T00:00:00Z
dc.identifier.none.fl_str_mv 10.1016/j.compbiomed.2021.105002
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/COVID-19_infection_localization_and_severity_grading_from_chest_X-ray_images/24314347
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Biomedical and clinical sciences
Cardiovascular medicine and haematology
Clinical sciences
Information and computing sciences
Artificial intelligence
COVID-19
Chest X-ray
Lung Segmentation
Infection Segmentation
Convolutional Neural Networks
Deep Learning
Reem Medical Center Qatar
dc.title.none.fl_str_mv COVID-19 infection localization and severity grading from chest X-ray images
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">The immense spread of coronavirus disease 2019 (COVID-19) has left healthcare systems incapable to diagnose and test patients at the required rate. Given the effects of COVID-19 on pulmonary tissues, chest radiographic imaging has become a necessity for screening and monitoring the disease. Numerous studies have proposed Deep Learning approaches for the automatic diagnosis of COVID-19. Although these methods achieved outstanding performance in detection, they have used limited chest X-ray (CXR) repositories for evaluation, usually with a few hundred COVID-19 CXR images only. Thus, such data scarcity prevents reliable evaluation of Deep Learning models with the potential of overfitting. In addition, most studies showed no or limited capability in infection localization and severity grading of COVID-19 pneumonia. In this study, we address this urgent need by proposing a systematic and unified approach for lung segmentation and COVID-19 localization with infection quantification from CXR images. To accomplish this, we have constructed the largest benchmark dataset with 33,920 CXR images, including 11,956 COVID-19 samples, where the annotation of ground-truth lung segmentation masks is performed on CXRs by an elegant human-machine collaborative approach. An extensive set of experiments was performed using the state-of-the-art segmentation networks, U-Net, U-Net++, and Feature Pyramid Networks (FPN). The developed network, after an iterative process, reached a superior performance for lung region segmentation with Intersection over Union (IoU) of 96.11% and Dice Similarity Coefficient (DSC) of 97.99%. Furthermore, COVID-19 infections of various shapes and types were reliably localized with 83.05% IoU and 88.21% DSC. Finally, the proposed approach has achieved an outstanding COVID-19 detection performance with both sensitivity and specificity values above 99%.</p><h2>Other Information</h2><p dir="ltr">Published in: Computers in Biology and Medicine<br>License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1016/j.compbiomed.2021.105002" target="_blank">https://dx.doi.org/10.1016/j.compbiomed.2021.105002</a></p>
eu_rights_str_mv openAccess
id Manara2_388281d96d22731432cd3b951b8b0ab1
identifier_str_mv 10.1016/j.compbiomed.2021.105002
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/24314347
publishDate 2021
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling COVID-19 infection localization and severity grading from chest X-ray imagesAnas M. Tahir (16870077)Muhammad E.H. Chowdhury (17151154)Amith Khandakar (14151981)Tawsifur Rahman (14150523)Yazan Qiblawey (16904838)Uzair Khurshid (17151157)Serkan Kiranyaz (3762058)Nabil Ibtehaz (16888773)M. Sohel Rahman (12056885)Somaya Al-Maadeed (5178131)Sakib Mahmud (15302404)Maymouna Ezeddin (16891368)Khaled Hameed (17151160)Tahir Hamid (16869921)Biomedical and clinical sciencesCardiovascular medicine and haematologyClinical sciencesInformation and computing sciencesArtificial intelligenceCOVID-19Chest X-rayLung SegmentationInfection SegmentationConvolutional Neural NetworksDeep LearningReem Medical Center Qatar<p dir="ltr">The immense spread of coronavirus disease 2019 (COVID-19) has left healthcare systems incapable to diagnose and test patients at the required rate. Given the effects of COVID-19 on pulmonary tissues, chest radiographic imaging has become a necessity for screening and monitoring the disease. Numerous studies have proposed Deep Learning approaches for the automatic diagnosis of COVID-19. Although these methods achieved outstanding performance in detection, they have used limited chest X-ray (CXR) repositories for evaluation, usually with a few hundred COVID-19 CXR images only. Thus, such data scarcity prevents reliable evaluation of Deep Learning models with the potential of overfitting. In addition, most studies showed no or limited capability in infection localization and severity grading of COVID-19 pneumonia. In this study, we address this urgent need by proposing a systematic and unified approach for lung segmentation and COVID-19 localization with infection quantification from CXR images. To accomplish this, we have constructed the largest benchmark dataset with 33,920 CXR images, including 11,956 COVID-19 samples, where the annotation of ground-truth lung segmentation masks is performed on CXRs by an elegant human-machine collaborative approach. An extensive set of experiments was performed using the state-of-the-art segmentation networks, U-Net, U-Net++, and Feature Pyramid Networks (FPN). The developed network, after an iterative process, reached a superior performance for lung region segmentation with Intersection over Union (IoU) of 96.11% and Dice Similarity Coefficient (DSC) of 97.99%. Furthermore, COVID-19 infections of various shapes and types were reliably localized with 83.05% IoU and 88.21% DSC. Finally, the proposed approach has achieved an outstanding COVID-19 detection performance with both sensitivity and specificity values above 99%.</p><h2>Other Information</h2><p dir="ltr">Published in: Computers in Biology and Medicine<br>License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1016/j.compbiomed.2021.105002" target="_blank">https://dx.doi.org/10.1016/j.compbiomed.2021.105002</a></p>2021-12-01T00:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1016/j.compbiomed.2021.105002https://figshare.com/articles/journal_contribution/COVID-19_infection_localization_and_severity_grading_from_chest_X-ray_images/24314347CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/243143472021-12-01T00:00:00Z
spellingShingle COVID-19 infection localization and severity grading from chest X-ray images
Anas M. Tahir (16870077)
Biomedical and clinical sciences
Cardiovascular medicine and haematology
Clinical sciences
Information and computing sciences
Artificial intelligence
COVID-19
Chest X-ray
Lung Segmentation
Infection Segmentation
Convolutional Neural Networks
Deep Learning
Reem Medical Center Qatar
status_str publishedVersion
title COVID-19 infection localization and severity grading from chest X-ray images
title_full COVID-19 infection localization and severity grading from chest X-ray images
title_fullStr COVID-19 infection localization and severity grading from chest X-ray images
title_full_unstemmed COVID-19 infection localization and severity grading from chest X-ray images
title_short COVID-19 infection localization and severity grading from chest X-ray images
title_sort COVID-19 infection localization and severity grading from chest X-ray images
topic Biomedical and clinical sciences
Cardiovascular medicine and haematology
Clinical sciences
Information and computing sciences
Artificial intelligence
COVID-19
Chest X-ray
Lung Segmentation
Infection Segmentation
Convolutional Neural Networks
Deep Learning
Reem Medical Center Qatar