Cargando…

Impact of Lung Segmentation on the Diagnosis and Explanation of COVID-19 in Chest X-ray Images

COVID-19 frequently provokes pneumonia, which can be diagnosed using imaging exams. Chest X-ray (CXR) is often useful because it is cheap, fast, widespread, and uses less radiation. Here, we demonstrate the impact of lung segmentation in COVID-19 identification using CXR images and evaluate which co...

Descripción completa

Detalles Bibliográficos
Autores principales: Teixeira, Lucas O., Pereira, Rodolfo M., Bertolini, Diego, Oliveira, Luiz S., Nanni, Loris, Cavalcanti, George D. C., Costa, Yandre M. G.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8587284/
https://www.ncbi.nlm.nih.gov/pubmed/34770423
http://dx.doi.org/10.3390/s21217116
_version_ 1784598101202305024
author Teixeira, Lucas O.
Pereira, Rodolfo M.
Bertolini, Diego
Oliveira, Luiz S.
Nanni, Loris
Cavalcanti, George D. C.
Costa, Yandre M. G.
author_facet Teixeira, Lucas O.
Pereira, Rodolfo M.
Bertolini, Diego
Oliveira, Luiz S.
Nanni, Loris
Cavalcanti, George D. C.
Costa, Yandre M. G.
author_sort Teixeira, Lucas O.
collection PubMed
description COVID-19 frequently provokes pneumonia, which can be diagnosed using imaging exams. Chest X-ray (CXR) is often useful because it is cheap, fast, widespread, and uses less radiation. Here, we demonstrate the impact of lung segmentation in COVID-19 identification using CXR images and evaluate which contents of the image influenced the most. Semantic segmentation was performed using a U-Net CNN architecture, and the classification using three CNN architectures (VGG, ResNet, and Inception). Explainable Artificial Intelligence techniques were employed to estimate the impact of segmentation. A three-classes database was composed: lung opacity (pneumonia), COVID-19, and normal. We assessed the impact of creating a CXR image database from different sources, and the COVID-19 generalization from one source to another. The segmentation achieved a Jaccard distance of 0.034 and a Dice coefficient of 0.982. The classification using segmented images achieved an F1-Score of 0.88 for the multi-class setup, and 0.83 for COVID-19 identification. In the cross-dataset scenario, we obtained an F1-Score of 0.74 and an area under the ROC curve of 0.9 for COVID-19 identification using segmented images. Experiments support the conclusion that even after segmentation, there is a strong bias introduced by underlying factors from different sources.
format Online
Article
Text
id pubmed-8587284
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-85872842021-11-13 Impact of Lung Segmentation on the Diagnosis and Explanation of COVID-19 in Chest X-ray Images Teixeira, Lucas O. Pereira, Rodolfo M. Bertolini, Diego Oliveira, Luiz S. Nanni, Loris Cavalcanti, George D. C. Costa, Yandre M. G. Sensors (Basel) Article COVID-19 frequently provokes pneumonia, which can be diagnosed using imaging exams. Chest X-ray (CXR) is often useful because it is cheap, fast, widespread, and uses less radiation. Here, we demonstrate the impact of lung segmentation in COVID-19 identification using CXR images and evaluate which contents of the image influenced the most. Semantic segmentation was performed using a U-Net CNN architecture, and the classification using three CNN architectures (VGG, ResNet, and Inception). Explainable Artificial Intelligence techniques were employed to estimate the impact of segmentation. A three-classes database was composed: lung opacity (pneumonia), COVID-19, and normal. We assessed the impact of creating a CXR image database from different sources, and the COVID-19 generalization from one source to another. The segmentation achieved a Jaccard distance of 0.034 and a Dice coefficient of 0.982. The classification using segmented images achieved an F1-Score of 0.88 for the multi-class setup, and 0.83 for COVID-19 identification. In the cross-dataset scenario, we obtained an F1-Score of 0.74 and an area under the ROC curve of 0.9 for COVID-19 identification using segmented images. Experiments support the conclusion that even after segmentation, there is a strong bias introduced by underlying factors from different sources. MDPI 2021-10-27 /pmc/articles/PMC8587284/ /pubmed/34770423 http://dx.doi.org/10.3390/s21217116 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Teixeira, Lucas O.
Pereira, Rodolfo M.
Bertolini, Diego
Oliveira, Luiz S.
Nanni, Loris
Cavalcanti, George D. C.
Costa, Yandre M. G.
Impact of Lung Segmentation on the Diagnosis and Explanation of COVID-19 in Chest X-ray Images
title Impact of Lung Segmentation on the Diagnosis and Explanation of COVID-19 in Chest X-ray Images
title_full Impact of Lung Segmentation on the Diagnosis and Explanation of COVID-19 in Chest X-ray Images
title_fullStr Impact of Lung Segmentation on the Diagnosis and Explanation of COVID-19 in Chest X-ray Images
title_full_unstemmed Impact of Lung Segmentation on the Diagnosis and Explanation of COVID-19 in Chest X-ray Images
title_short Impact of Lung Segmentation on the Diagnosis and Explanation of COVID-19 in Chest X-ray Images
title_sort impact of lung segmentation on the diagnosis and explanation of covid-19 in chest x-ray images
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8587284/
https://www.ncbi.nlm.nih.gov/pubmed/34770423
http://dx.doi.org/10.3390/s21217116
work_keys_str_mv AT teixeiralucaso impactoflungsegmentationonthediagnosisandexplanationofcovid19inchestxrayimages
AT pereirarodolfom impactoflungsegmentationonthediagnosisandexplanationofcovid19inchestxrayimages
AT bertolinidiego impactoflungsegmentationonthediagnosisandexplanationofcovid19inchestxrayimages
AT oliveiraluizs impactoflungsegmentationonthediagnosisandexplanationofcovid19inchestxrayimages
AT nanniloris impactoflungsegmentationonthediagnosisandexplanationofcovid19inchestxrayimages
AT cavalcantigeorgedc impactoflungsegmentationonthediagnosisandexplanationofcovid19inchestxrayimages
AT costayandremg impactoflungsegmentationonthediagnosisandexplanationofcovid19inchestxrayimages