An Ensemble of Global and Local-Attention Based Convolutional Neural Networks for COVID-19 Diagnosis on Chest X-ray Images
The recent Coronavirus Disease 2019 (COVID-19) pandemic has put a tremendous burden on global health systems. Medical practitioners are under great pressure for reliable screening of suspected cases employing adjunct diagnostic tools to standard point-of-care testing methodology. Chest X-rays (CXRs)...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-01-01
|
Series: | Symmetry |
Subjects: | |
Online Access: | https://www.mdpi.com/2073-8994/13/1/113 |
_version_ | 1797413147242397696 |
---|---|
author | Ahmed Afifi Noor E Hafsa Mona A. S. Ali Abdulaziz Alhumam Safa Alsalman |
author_facet | Ahmed Afifi Noor E Hafsa Mona A. S. Ali Abdulaziz Alhumam Safa Alsalman |
author_sort | Ahmed Afifi |
collection | DOAJ |
description | The recent Coronavirus Disease 2019 (COVID-19) pandemic has put a tremendous burden on global health systems. Medical practitioners are under great pressure for reliable screening of suspected cases employing adjunct diagnostic tools to standard point-of-care testing methodology. Chest X-rays (CXRs) are appearing as a prospective diagnostic tool with easy-to-acquire, low-cost and less cross-contamination risk features. Artificial intelligence (AI)-attributed CXR evaluation has shown great potential for distinguishing COVID-19-induced pneumonia from other associated clinical instances. However, one of the associated challenges with diagnostic imaging-based modeling is incorrect feature attribution, which leads the model to learn misguiding disease patterns, causing wrong predictions. Here, we demonstrate an effective deep learning-based methodology to mitigate the problem, thereby allowing the classification algorithm to learn from relevant features. The proposed deep-learning framework consists of an ensemble of convolutional neural network (CNN) models focusing on both global and local pathological features from CXR lung images, while the latter is extracted using a multi-instance learning scheme and a local attention mechanism. An inspection of a series of backbone CNN models using global and local features, and an ensemble of both features, trained from high-quality CXR images of 1311 patients, further augmented for achieving the symmetry in class distribution, to localize lung pathological features followed by the classification of COVID-19 and other related pneumonia, shows that a DenseNet161 architecture outperforms all other models, as evaluated on an independent test set of 159 patients with confirmed cases. Specifically, an ensemble of DenseNet161 models with global and local attention-based features achieve an average balanced accuracy of 91.2%, average precision of 92.4%, and F1-score of 91.9% in a multi-label classification framework comprising COVID-19, pneumonia, and control classes. The DenseNet161 ensembles were also found to be statistically significant from all other models in a comprehensive statistical analysis. The current study demonstrated that the proposed deep learning-based algorithm can accurately identify the COVID-19-related pneumonia in CXR images, along with differentiating non-COVID-19-associated pneumonia with high specificity, by effectively alleviating the incorrect feature attribution problem, and exploiting an enhanced feature descriptor. |
first_indexed | 2024-03-09T05:13:25Z |
format | Article |
id | doaj.art-c4190d7270cb444e834e8b3177d7c1c9 |
institution | Directory Open Access Journal |
issn | 2073-8994 |
language | English |
last_indexed | 2024-03-09T05:13:25Z |
publishDate | 2021-01-01 |
publisher | MDPI AG |
record_format | Article |
series | Symmetry |
spelling | doaj.art-c4190d7270cb444e834e8b3177d7c1c92023-12-03T12:47:46ZengMDPI AGSymmetry2073-89942021-01-0113111310.3390/sym13010113An Ensemble of Global and Local-Attention Based Convolutional Neural Networks for COVID-19 Diagnosis on Chest X-ray ImagesAhmed Afifi0Noor E Hafsa1Mona A. S. Ali2Abdulaziz Alhumam3Safa Alsalman4Department of Computer Science, College of Computer Science and Information Technology, King Faisal University, P.O. Box 400, Al-Ahsa 31982, Saudi ArabiaDepartment of Computer Science, College of Computer Science and Information Technology, King Faisal University, P.O. Box 400, Al-Ahsa 31982, Saudi ArabiaDepartment of Computer Science, College of Computer Science and Information Technology, King Faisal University, P.O. Box 400, Al-Ahsa 31982, Saudi ArabiaDepartment of Computer Science, College of Computer Science and Information Technology, King Faisal University, P.O. Box 400, Al-Ahsa 31982, Saudi ArabiaDepartment of Computer Science, College of Computer Science and Information Technology, King Faisal University, P.O. Box 400, Al-Ahsa 31982, Saudi ArabiaThe recent Coronavirus Disease 2019 (COVID-19) pandemic has put a tremendous burden on global health systems. Medical practitioners are under great pressure for reliable screening of suspected cases employing adjunct diagnostic tools to standard point-of-care testing methodology. Chest X-rays (CXRs) are appearing as a prospective diagnostic tool with easy-to-acquire, low-cost and less cross-contamination risk features. Artificial intelligence (AI)-attributed CXR evaluation has shown great potential for distinguishing COVID-19-induced pneumonia from other associated clinical instances. However, one of the associated challenges with diagnostic imaging-based modeling is incorrect feature attribution, which leads the model to learn misguiding disease patterns, causing wrong predictions. Here, we demonstrate an effective deep learning-based methodology to mitigate the problem, thereby allowing the classification algorithm to learn from relevant features. The proposed deep-learning framework consists of an ensemble of convolutional neural network (CNN) models focusing on both global and local pathological features from CXR lung images, while the latter is extracted using a multi-instance learning scheme and a local attention mechanism. An inspection of a series of backbone CNN models using global and local features, and an ensemble of both features, trained from high-quality CXR images of 1311 patients, further augmented for achieving the symmetry in class distribution, to localize lung pathological features followed by the classification of COVID-19 and other related pneumonia, shows that a DenseNet161 architecture outperforms all other models, as evaluated on an independent test set of 159 patients with confirmed cases. Specifically, an ensemble of DenseNet161 models with global and local attention-based features achieve an average balanced accuracy of 91.2%, average precision of 92.4%, and F1-score of 91.9% in a multi-label classification framework comprising COVID-19, pneumonia, and control classes. The DenseNet161 ensembles were also found to be statistically significant from all other models in a comprehensive statistical analysis. The current study demonstrated that the proposed deep learning-based algorithm can accurately identify the COVID-19-related pneumonia in CXR images, along with differentiating non-COVID-19-associated pneumonia with high specificity, by effectively alleviating the incorrect feature attribution problem, and exploiting an enhanced feature descriptor.https://www.mdpi.com/2073-8994/13/1/113COVID-19 detectionpneumonia diagnosisconvolutional neural networkmulti-instance learningwrong feature attributionmulti-label classification |
spellingShingle | Ahmed Afifi Noor E Hafsa Mona A. S. Ali Abdulaziz Alhumam Safa Alsalman An Ensemble of Global and Local-Attention Based Convolutional Neural Networks for COVID-19 Diagnosis on Chest X-ray Images Symmetry COVID-19 detection pneumonia diagnosis convolutional neural network multi-instance learning wrong feature attribution multi-label classification |
title | An Ensemble of Global and Local-Attention Based Convolutional Neural Networks for COVID-19 Diagnosis on Chest X-ray Images |
title_full | An Ensemble of Global and Local-Attention Based Convolutional Neural Networks for COVID-19 Diagnosis on Chest X-ray Images |
title_fullStr | An Ensemble of Global and Local-Attention Based Convolutional Neural Networks for COVID-19 Diagnosis on Chest X-ray Images |
title_full_unstemmed | An Ensemble of Global and Local-Attention Based Convolutional Neural Networks for COVID-19 Diagnosis on Chest X-ray Images |
title_short | An Ensemble of Global and Local-Attention Based Convolutional Neural Networks for COVID-19 Diagnosis on Chest X-ray Images |
title_sort | ensemble of global and local attention based convolutional neural networks for covid 19 diagnosis on chest x ray images |
topic | COVID-19 detection pneumonia diagnosis convolutional neural network multi-instance learning wrong feature attribution multi-label classification |
url | https://www.mdpi.com/2073-8994/13/1/113 |
work_keys_str_mv | AT ahmedafifi anensembleofglobalandlocalattentionbasedconvolutionalneuralnetworksforcovid19diagnosisonchestxrayimages AT noorehafsa anensembleofglobalandlocalattentionbasedconvolutionalneuralnetworksforcovid19diagnosisonchestxrayimages AT monaasali anensembleofglobalandlocalattentionbasedconvolutionalneuralnetworksforcovid19diagnosisonchestxrayimages AT abdulazizalhumam anensembleofglobalandlocalattentionbasedconvolutionalneuralnetworksforcovid19diagnosisonchestxrayimages AT safaalsalman anensembleofglobalandlocalattentionbasedconvolutionalneuralnetworksforcovid19diagnosisonchestxrayimages AT ahmedafifi ensembleofglobalandlocalattentionbasedconvolutionalneuralnetworksforcovid19diagnosisonchestxrayimages AT noorehafsa ensembleofglobalandlocalattentionbasedconvolutionalneuralnetworksforcovid19diagnosisonchestxrayimages AT monaasali ensembleofglobalandlocalattentionbasedconvolutionalneuralnetworksforcovid19diagnosisonchestxrayimages AT abdulazizalhumam ensembleofglobalandlocalattentionbasedconvolutionalneuralnetworksforcovid19diagnosisonchestxrayimages AT safaalsalman ensembleofglobalandlocalattentionbasedconvolutionalneuralnetworksforcovid19diagnosisonchestxrayimages |