Pneumonia prediction using deep learning in chest X-ray Images

Md. Maniruzzaman 1, 2, *, Anhar Sami 3, 4, Rahmanul Hoque 5 and Pabitra Mandal 6

1 Department of Electrical Engineering, School of Engineering, San Francisco Bay University, Fremont, CA 94539, USA
2 Department of Electrical and Computer Engineering, North South University, Dhaka-1229, Bangladesh.
3 Department of Electrical and Computer Engineering, Missouri University of Science and Technology, Rolla, MO 65401, USA.
4 Electrical and Computer Engineering, Altinbas University, Istanbul, Turkey.
5 Department of Computer Science, North Dakota State University, Fargo, North Dakota, ND 58105, USA.
6 Medical Assistant Training School, Bagerhat, Bangladesh.
6 Bandhan Private Hospital, Faridpur, Bangladesh.
 
Research Article
International Journal of Science and Research Archive, 2024, 12(01), 767–773.
Article DOI: 10.30574/ijsra.2024.12.1.0880
Publication history: 
Received on 12 April 2024; revised on 18 May 2024; accepted on 21 May 2024
 
Abstract: 
Pneumonia, a potentially fatal lung disease caused by viral or bacterial infection, poses challenges in diagnosis from chest X-ray images due to similarities with other lung infections. This research aims to develop a computer-aided system for pneumonia detection in children, enhancing diagnostic accuracy. In this paper, five established deep learning models such as VGG-16, VGG-19, ResNet-50, Inception-V3, Xception pre-trained on ImageNet have been used. These models have been applied on the chest X-ray dataset to optimize performance. Xception provides recall, specificity, accuracy and AUC of 97.43%, 91.02%, 95.06% and 94.23%, respectively.
 
Keywords: 
Lung diseases; X-ray imaging; Deep learning; Pneumonia; Transfer learning; Exception; VGG-16, VGG-19; ResNet-50; Inception-V3. 
 
Full text article in PDF: 
 
Copyright information: 

Copyright © 2024 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0