COVID-19 Diagnosis on Chest X-Ray Images using an Xception-based Deep Learning Classifier and Gradient-weighted Class Activation Mapping

Diego Maldonado; Ricardo Araguillin; Felipe Grijalva; Diego S. Benitez; Noel Perez

doi:10.1109/ColCACI59285.2023.10225933

COVID-19 Diagnosis on Chest X-Ray Images using an Xception-based Deep Learning Classifier and Gradient-weighted Class Activation Mapping

Diego Maldonado
, Ricardo Araguillin
, Felipe Grijalva
, Diego S. Benitez
, Noel Perez

Escuela Politecnica Nacional

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

This paper proposes the development of a deep learning model for diagnosing COVID-19 through the analysis of chest X-ray images. First, data augmentation is implemented to avoid overfitting and improve model generalization. Then, instead of conventional image segmentation techniques, Gradient-weighted Class Activation Mapping (Grad-CAM) is used to highlight the important regions directly related to COVID-19. Subsequently, transfer learning is implemented to transform the data of the X-ray images to a reduced set of features using the Xception convolutional neural network. Finally, a classification neural network is designed, parameterized and trained, which is capable of recognizing healthy patients with 97% accuracy, while the detection rate for patients infected with COVID-19 was 92%.

Original language	English
Title of host publication	2023 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2023 - Proceedings
Editors	Alvaro David Orjuela-Canon
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9798350316599
DOIs	https://doi.org/10.1109/ColCACI59285.2023.10225933
State	Published - 26 Jul 2023
Event	2023 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2023 - Bogota, Colombia Duration: 26 Jul 2023 → 28 Jul 2023

Publication series

Name	2023 IEEE Colombian Conference on Applications of Computational Intelligence (ColCACI)

Conference

Conference	2023 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2023
Country/Territory	Colombia
City	Bogota
Period	26/07/23 → 28/07/23

Keywords

COVID-19
NNs
Xception
computer X-ray diagnostic tool
deep learning
transfer learning

Access to Document

10.1109/ColCACI59285.2023.10225933

Cite this

Maldonado, D., Araguillin, R., Grijalva, F., Benitez, D. S., & Perez, N. (2023). COVID-19 Diagnosis on Chest X-Ray Images using an Xception-based Deep Learning Classifier and Gradient-weighted Class Activation Mapping. In A. D. Orjuela-Canon (Ed.), 2023 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2023 - Proceedings (2023 IEEE Colombian Conference on Applications of Computational Intelligence (ColCACI)). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ColCACI59285.2023.10225933

Maldonado, Diego ; Araguillin, Ricardo ; Grijalva, Felipe et al. / COVID-19 Diagnosis on Chest X-Ray Images using an Xception-based Deep Learning Classifier and Gradient-weighted Class Activation Mapping. 2023 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2023 - Proceedings. editor / Alvaro David Orjuela-Canon. Institute of Electrical and Electronics Engineers Inc., 2023. (2023 IEEE Colombian Conference on Applications of Computational Intelligence (ColCACI)).

@inproceedings{f99c5bb26f2d48c7b3ade1ea9b6729c8,

title = "COVID-19 Diagnosis on Chest X-Ray Images using an Xception-based Deep Learning Classifier and Gradient-weighted Class Activation Mapping",

abstract = "This paper proposes the development of a deep learning model for diagnosing COVID-19 through the analysis of chest X-ray images. First, data augmentation is implemented to avoid overfitting and improve model generalization. Then, instead of conventional image segmentation techniques, Gradient-weighted Class Activation Mapping (Grad-CAM) is used to highlight the important regions directly related to COVID-19. Subsequently, transfer learning is implemented to transform the data of the X-ray images to a reduced set of features using the Xception convolutional neural network. Finally, a classification neural network is designed, parameterized and trained, which is capable of recognizing healthy patients with 97\% accuracy, while the detection rate for patients infected with COVID-19 was 92\%.",

keywords = "COVID-19, NNs, Xception, computer X-ray diagnostic tool, deep learning, transfer learning",

author = "Diego Maldonado and Ricardo Araguillin and Felipe Grijalva and Benitez, \{Diego S.\} and Noel Perez",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2023 ; Conference date: 26-07-2023 Through 28-07-2023",

year = "2023",

month = jul,

day = "26",

doi = "10.1109/ColCACI59285.2023.10225933",

language = "Ingl{\'e}s",

series = "2023 IEEE Colombian Conference on Applications of Computational Intelligence (ColCACI)",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

editor = "Orjuela-Canon, \{Alvaro David\}",

booktitle = "2023 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2023 - Proceedings",

}

Maldonado, D, Araguillin, R, Grijalva, F , Benitez, DS & Perez, N 2023, COVID-19 Diagnosis on Chest X-Ray Images using an Xception-based Deep Learning Classifier and Gradient-weighted Class Activation Mapping. in AD Orjuela-Canon (ed.), 2023 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2023 - Proceedings. 2023 IEEE Colombian Conference on Applications of Computational Intelligence (ColCACI), Institute of Electrical and Electronics Engineers Inc., 2023 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2023, Bogota, Colombia, 26/07/23. https://doi.org/10.1109/ColCACI59285.2023.10225933

COVID-19 Diagnosis on Chest X-Ray Images using an Xception-based Deep Learning Classifier and Gradient-weighted Class Activation Mapping. / Maldonado, Diego; Araguillin, Ricardo; Grijalva, Felipe et al.
2023 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2023 - Proceedings. ed. / Alvaro David Orjuela-Canon. Institute of Electrical and Electronics Engineers Inc., 2023. (2023 IEEE Colombian Conference on Applications of Computational Intelligence (ColCACI)).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - COVID-19 Diagnosis on Chest X-Ray Images using an Xception-based Deep Learning Classifier and Gradient-weighted Class Activation Mapping

AU - Maldonado, Diego

AU - Araguillin, Ricardo

AU - Grijalva, Felipe

AU - Benitez, Diego S.

AU - Perez, Noel

PY - 2023/7/26

Y1 - 2023/7/26

N2 - This paper proposes the development of a deep learning model for diagnosing COVID-19 through the analysis of chest X-ray images. First, data augmentation is implemented to avoid overfitting and improve model generalization. Then, instead of conventional image segmentation techniques, Gradient-weighted Class Activation Mapping (Grad-CAM) is used to highlight the important regions directly related to COVID-19. Subsequently, transfer learning is implemented to transform the data of the X-ray images to a reduced set of features using the Xception convolutional neural network. Finally, a classification neural network is designed, parameterized and trained, which is capable of recognizing healthy patients with 97% accuracy, while the detection rate for patients infected with COVID-19 was 92%.

AB - This paper proposes the development of a deep learning model for diagnosing COVID-19 through the analysis of chest X-ray images. First, data augmentation is implemented to avoid overfitting and improve model generalization. Then, instead of conventional image segmentation techniques, Gradient-weighted Class Activation Mapping (Grad-CAM) is used to highlight the important regions directly related to COVID-19. Subsequently, transfer learning is implemented to transform the data of the X-ray images to a reduced set of features using the Xception convolutional neural network. Finally, a classification neural network is designed, parameterized and trained, which is capable of recognizing healthy patients with 97% accuracy, while the detection rate for patients infected with COVID-19 was 92%.

KW - COVID-19

KW - NNs

KW - Xception

KW - computer X-ray diagnostic tool

KW - deep learning

KW - transfer learning

UR - https://www.scopus.com/pages/publications/85171616538

U2 - 10.1109/ColCACI59285.2023.10225933

DO - 10.1109/ColCACI59285.2023.10225933

M3 - Contribución a la conferencia

AN - SCOPUS:85171616538

T3 - 2023 IEEE Colombian Conference on Applications of Computational Intelligence (ColCACI)

BT - 2023 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2023 - Proceedings

A2 - Orjuela-Canon, Alvaro David

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2023 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2023

Y2 - 26 July 2023 through 28 July 2023

ER -

Maldonado D, Araguillin R, Grijalva F , Benitez DS , Perez N. COVID-19 Diagnosis on Chest X-Ray Images using an Xception-based Deep Learning Classifier and Gradient-weighted Class Activation Mapping. In Orjuela-Canon AD, editor, 2023 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2023 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2023. (2023 IEEE Colombian Conference on Applications of Computational Intelligence (ColCACI)). doi: 10.1109/ColCACI59285.2023.10225933

COVID-19 Diagnosis on Chest X-Ray Images using an Xception-based Deep Learning Classifier and Gradient-weighted Class Activation Mapping

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this