A Transfer Learning Scheme for COVID-19 Diagnosis from Chest X-Ray Images Using Gradient-Weighted Class Activation Mapping

Ricardo Araguillin; Diego Maldonado; Felipe Grijalva; Diego S. Benítez; Noel Pérez-Pérez

doi:10.1007/978-3-031-48415-5_1

A Transfer Learning Scheme for COVID-19 Diagnosis from Chest X-Ray Images Using Gradient-Weighted Class Activation Mapping

Ricardo Araguillin, Diego Maldonado, Felipe Grijalva, Diego S. Benítez, Noel Pérez-Pérez

Escuela Politecnica Nacional

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

Abstract

This paper proposes a new method for detecting COVID-19 in chest X-ray images by comparing it with existing models. Our proposed deep learning model is customized for an accurate diagnosis of COVID-19. To improve model performance and prevent overfitting, we first apply data augmentation techniques. Unlike traditional image segmentation methods, we use gradient-weighted class activation mapping (Grad-CAM) to highlight regions critical to identifying COVID-19. We then used transfer learning of Xception convolutional neural networks to extract the X-ray image data into a compact feature set. Finally, we design, parameterize, and train the neural classification network. The network showed impressive results, achieving an astonishing 97% accuracy in identifying healthy patients. At the same time, its detection rate in COVID-19-infected patients was 92%, making it a worthy competitor compared to other detection models.

Original language	English
Title of host publication	Applications of Computational Intelligence - 6th IEEE Colombian Conference, ColCACI 2023, Revised Selected Papers
Editors	Alvaro David Orjuela-Cañón, Jesus A Lopez, Julián David Arias-Londoño
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	3-18
Number of pages	16
ISBN (Print)	9783031484148
DOIs	https://doi.org/10.1007/978-3-031-48415-5_1
State	Published - 2024
Event	6th IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2023 - Bogota, Colombia Duration: 26 Jul 2023 → 28 Jul 2023

Publication series

Name	Communications in Computer and Information Science
Volume	1865 CCIS
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	6th 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
MobilNetV2
NNs
Xception
computer X-ray diagnostic tool
deep learning
transfer learning

Access to Document

10.1007/978-3-031-48415-5_1

Cite this

Araguillin, R., Maldonado, D., Grijalva, F., Benítez, D. S., & Pérez-Pérez, N. (2024). A Transfer Learning Scheme for COVID-19 Diagnosis from Chest X-Ray Images Using Gradient-Weighted Class Activation Mapping. In A. D. Orjuela-Cañón, J. A. Lopez, & J. D. Arias-Londoño (Eds.), Applications of Computational Intelligence - 6th IEEE Colombian Conference, ColCACI 2023, Revised Selected Papers (pp. 3-18). (Communications in Computer and Information Science; Vol. 1865 CCIS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-48415-5_1

Araguillin, Ricardo ; Maldonado, Diego ; Grijalva, Felipe et al. / A Transfer Learning Scheme for COVID-19 Diagnosis from Chest X-Ray Images Using Gradient-Weighted Class Activation Mapping. Applications of Computational Intelligence - 6th IEEE Colombian Conference, ColCACI 2023, Revised Selected Papers. editor / Alvaro David Orjuela-Cañón ; Jesus A Lopez ; Julián David Arias-Londoño. Springer Science and Business Media Deutschland GmbH, 2024. pp. 3-18 (Communications in Computer and Information Science).

@inproceedings{5064d9cc49b348ba8fb09f4b0428dc6c,

title = "A Transfer Learning Scheme for COVID-19 Diagnosis from Chest X-Ray Images Using Gradient-Weighted Class Activation Mapping",

abstract = "This paper proposes a new method for detecting COVID-19 in chest X-ray images by comparing it with existing models. Our proposed deep learning model is customized for an accurate diagnosis of COVID-19. To improve model performance and prevent overfitting, we first apply data augmentation techniques. Unlike traditional image segmentation methods, we use gradient-weighted class activation mapping (Grad-CAM) to highlight regions critical to identifying COVID-19. We then used transfer learning of Xception convolutional neural networks to extract the X-ray image data into a compact feature set. Finally, we design, parameterize, and train the neural classification network. The network showed impressive results, achieving an astonishing 97% accuracy in identifying healthy patients. At the same time, its detection rate in COVID-19-infected patients was 92%, making it a worthy competitor compared to other detection models.",

keywords = "COVID-19, MobilNetV2, NNs, Xception, computer X-ray diagnostic tool, deep learning, transfer learning",

author = "Ricardo Araguillin and Diego Maldonado and Felipe Grijalva and Ben{\'i}tez, {Diego S.} and Noel P{\'e}rez-P{\'e}rez",

note = "Publisher Copyright: {\textcopyright} 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.; 6th IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2023 ; Conference date: 26-07-2023 Through 28-07-2023",

year = "2024",

doi = "10.1007/978-3-031-48415-5_1",

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

isbn = "9783031484148",

series = "Communications in Computer and Information Science",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "3--18",

editor = "Orjuela-Ca{\~n}{\'o}n, {Alvaro David} and Lopez, {Jesus A} and Arias-Londo{\~n}o, {Juli{\'a}n David}",

booktitle = "Applications of Computational Intelligence - 6th IEEE Colombian Conference, ColCACI 2023, Revised Selected Papers",

}

Araguillin, R, Maldonado, D, Grijalva, F , Benítez, DS & Pérez-Pérez, N 2024, A Transfer Learning Scheme for COVID-19 Diagnosis from Chest X-Ray Images Using Gradient-Weighted Class Activation Mapping. in AD Orjuela-Cañón, JA Lopez & JD Arias-Londoño (eds), Applications of Computational Intelligence - 6th IEEE Colombian Conference, ColCACI 2023, Revised Selected Papers. Communications in Computer and Information Science, vol. 1865 CCIS, Springer Science and Business Media Deutschland GmbH, pp. 3-18, 6th IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2023, Bogota, Colombia, 26/07/23. https://doi.org/10.1007/978-3-031-48415-5_1

A Transfer Learning Scheme for COVID-19 Diagnosis from Chest X-Ray Images Using Gradient-Weighted Class Activation Mapping. / Araguillin, Ricardo; Maldonado, Diego; Grijalva, Felipe et al.
Applications of Computational Intelligence - 6th IEEE Colombian Conference, ColCACI 2023, Revised Selected Papers. ed. / Alvaro David Orjuela-Cañón; Jesus A Lopez; Julián David Arias-Londoño. Springer Science and Business Media Deutschland GmbH, 2024. p. 3-18 (Communications in Computer and Information Science; Vol. 1865 CCIS).

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

TY - GEN

T1 - A Transfer Learning Scheme for COVID-19 Diagnosis from Chest X-Ray Images Using Gradient-Weighted Class Activation Mapping

AU - Araguillin, Ricardo

AU - Maldonado, Diego

AU - Grijalva, Felipe

AU - Benítez, Diego S.

AU - Pérez-Pérez, Noel

PY - 2024

Y1 - 2024

N2 - This paper proposes a new method for detecting COVID-19 in chest X-ray images by comparing it with existing models. Our proposed deep learning model is customized for an accurate diagnosis of COVID-19. To improve model performance and prevent overfitting, we first apply data augmentation techniques. Unlike traditional image segmentation methods, we use gradient-weighted class activation mapping (Grad-CAM) to highlight regions critical to identifying COVID-19. We then used transfer learning of Xception convolutional neural networks to extract the X-ray image data into a compact feature set. Finally, we design, parameterize, and train the neural classification network. The network showed impressive results, achieving an astonishing 97% accuracy in identifying healthy patients. At the same time, its detection rate in COVID-19-infected patients was 92%, making it a worthy competitor compared to other detection models.

AB - This paper proposes a new method for detecting COVID-19 in chest X-ray images by comparing it with existing models. Our proposed deep learning model is customized for an accurate diagnosis of COVID-19. To improve model performance and prevent overfitting, we first apply data augmentation techniques. Unlike traditional image segmentation methods, we use gradient-weighted class activation mapping (Grad-CAM) to highlight regions critical to identifying COVID-19. We then used transfer learning of Xception convolutional neural networks to extract the X-ray image data into a compact feature set. Finally, we design, parameterize, and train the neural classification network. The network showed impressive results, achieving an astonishing 97% accuracy in identifying healthy patients. At the same time, its detection rate in COVID-19-infected patients was 92%, making it a worthy competitor compared to other detection models.

KW - COVID-19

KW - MobilNetV2

KW - NNs

KW - Xception

KW - computer X-ray diagnostic tool

KW - deep learning

KW - transfer learning

UR - http://www.scopus.com/inward/record.url?scp=85177827505&partnerID=8YFLogxK

U2 - 10.1007/978-3-031-48415-5_1

DO - 10.1007/978-3-031-48415-5_1

M3 - Contribución a la conferencia

AN - SCOPUS:85177827505

SN - 9783031484148

T3 - Communications in Computer and Information Science

SP - 3

EP - 18

BT - Applications of Computational Intelligence - 6th IEEE Colombian Conference, ColCACI 2023, Revised Selected Papers

A2 - Orjuela-Cañón, Alvaro David

A2 - Lopez, Jesus A

A2 - Arias-Londoño, Julián David

PB - Springer Science and Business Media Deutschland GmbH

T2 - 6th IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2023

Y2 - 26 July 2023 through 28 July 2023

ER -

Araguillin R, Maldonado D, Grijalva F , Benítez DS , Pérez-Pérez N. A Transfer Learning Scheme for COVID-19 Diagnosis from Chest X-Ray Images Using Gradient-Weighted Class Activation Mapping. In Orjuela-Cañón AD, Lopez JA, Arias-Londoño JD, editors, Applications of Computational Intelligence - 6th IEEE Colombian Conference, ColCACI 2023, Revised Selected Papers. Springer Science and Business Media Deutschland GmbH. 2024. p. 3-18. (Communications in Computer and Information Science). doi: 10.1007/978-3-031-48415-5_1