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
N1 - Publisher Copyright:
© 2023 IEEE.
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 -