Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 Oct 27;21(21):7116.
doi: 10.3390/s21217116.

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

Lucas O Teixeira  1 , Rodolfo M Pereira  2 , Diego Bertolini  3 , Luiz S Oliveira  4 , Loris Nanni  5 , George D C Cavalcanti  6 , Yandre M G Costa  1
Affiliations

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

Lucas O Teixeira et al. Sensors (Basel). .

Abstract

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.

Keywords: COVID-19; chest X-ray; explainable artificial intelligence; semantic segmentation.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Proposed methodology.
Figure 2
Figure 2
Lungs segmentation on CXR image. (a) CXR image. (b) Binary mask. (c) Segmented lungs.
Figure 3
Figure 3
CXR with burned-in annotations. (a) Example 1. (b) Example 2.
Figure 4
Figure 4
Custom U-Net architecture.
Figure 5
Figure 5
RYDLS-20-v2 image samples. (a) Lung opacity. (b) COVID-19. (c) Normal.
Figure 6
Figure 6
Data augmentation examples.
Figure 7
Figure 7
LIME example. (a) Full CXR image. (b) Segmented CXR image.
Figure 8
Figure 8
Grad-CAM example. (a) Full CXR image. (b) Segmented CXR image.
Figure 9
Figure 9
COVID-19 Generalization ROC Curve.
Figure 10
Figure 10
LIME heatmaps. (a) VGG16. (b) ResNet50V2. (c) InceptionV3.
Figure 11
Figure 11
Grad-CAM heatmaps. (a) VGG16. (b) ResNet50V2. (c) InceptionV3.
Figure 12
Figure 12
F1-Score results boxplot stratified by segmentation.
Figure 13
Figure 13
Grad-CAM showing a large gradient on CXR annotations. (a) Example 1. (b) Example 2.
Figure 14
Figure 14
F1-Score results boxplot stratified by segmentation and model.
Figure 15
Figure 15
Segmented InceptionV3 Confusion Matrix.
See this image and copyright information in PMC

References

    1. Tay M.Z., Poh C.M., Rénia L., MacAry P.A., Ng L.F. The trinity of COVID-19: Immunity, inflammation and intervention. Nat. Rev. Immunol. 2020;20:363–374. doi: 10.1038/s41577-020-0311-8. - DOI - PMC - PubMed
    1. Lauer S.A., Grantz K.H., Bi Q., Jones F.K., Zheng Q., Meredith H.R., Azman A.S., Reich N.G., Lessler J. The incubation period of coronavirus disease 2019 (COVID-19) from publicly reported confirmed cases: Estimation and application. Ann. Intern. Med. 2020;172:577–582. doi: 10.7326/M20-0504. - DOI - PMC - PubMed
    1. Alimadadi A., Aryal S., Manandhar I., Munroe P.B., Joe B., Cheng X. Artificial Intelligence and Machine Learning to Fight COVID-19. Physiol. Genom. 2020;52:200–202. doi: 10.1152/physiolgenomics.00029.2020. - DOI - PMC - PubMed
    1. Self W.H., Courtney D.M., McNaughton C.D., Wunderink R.G., Kline J.A. High discordance of chest X-ray and computed tomography for detection of pulmonary opacities in ED patients: Implications for diagnosing pneumonia. Am. J. Emerg. Med. 2013;31:401–405. doi: 10.1016/j.ajem.2012.08.041. - DOI - PMC - PubMed
    1. Pereira R.M., Bertolini D., Teixeira L.O., Silla C.N., Jr., Costa Y.M.G. COVID-19 identification in chest X-ray images on flat and hierarchical classification scenarios. Comput. Methods Programs Biomed. 2020;194:105532. doi: 10.1016/j.cmpb.2020.105532. - DOI - PMC - PubMed