ORIGINAL ARTICLE
Automated COVID-19 detection in chest X-ray images using
fine-tuned deep learning architectures
Sonam Aggarwal
1
| Sheifali Gupta
1
| Adi Alhudhaif
2
| Deepika Koundal
3
|
Rupesh Gupta
1
| Kemal Polat
4
1
Chitkara University Institute of Engineering
and Technology, Chitkara University,
Chandigarh, Punjab, India
2
Department of Computer Science, College of
Computer Engineering and Sciences in Al-
kharj, Prince Sattam Bin Abdulaziz University,
Al-Kharj, Saudi Arabia
3
Department of Virtualization, School of
Computer Science, Dehradun, Uttarakhand,
India
4
Department of Electrical and Electronics
Engineering, Faculty of Engineering, Bolu
Abant Izzet Baysal University, Bolu, Turkey
Correspondence
Adi Alhudhaif, Department of Computer
Science, College of Computer Engineering and
Sciences in Al-kharj, Prince Sattam bin
Abdulaziz University, P.O. Box 151, Al-Kharj
11942, Saudi Arabia.
Email: a.alhudhaif@psau.edu.sa
Abstract
The COVID-19 pandemic has a significant impact on human health globally. The ill-
ness is due to the presence of a virus manifesting itself in a widespread disease
resulting in a high mortality rate in the whole world. According to the study, infected
patients have distinct radiographic visual characteristics as well as dry cough, breath-
lessness, fever, and other symptoms. Although, the reverse transcription polymerase-
chain reaction (RT-PCR) test has been used for COVID-19 testing its reliability is very
low. Therefore, computed tomography and X-ray images have been widely used.
Artificial intelligence coupled with X-ray technologies has recently shown to be more
effective in the diagnosis of this disease. With this motivation, a comparative analysis
of fine-tuned deep learning architectures has been made to speed up the detection
and classification of COVID-19 patients from other pneumonia groups. The models
used for this analysis are MobileNetV2, ResNet50, InceptionV3, NASNetMobile,
VGG16, Xception, InceptionResNetV2 DenseNet121, which have been fine-tuned
using a new set of layers replaced with the head of the network. This research work
has carried out an analysis on two datasets. Dataset-1 includes the images of three
classes: Normal, COVID, and Pneumonia. Dataset-2, in contrast, contains the same
classes with more focus on two prominent pneumonia categories: bacterial pneumo-
nia and viral pneumonia. The research was conducted on 959 X-ray images (250 of
Bacterial Pneumonia, 250 of Viral Pneumonia, 209 of COVID, and 250 of Normal
cases). Using the confusion matrix, the required results of different models have been
computed. For the first dataset, DenseNet121 has obtained a 97% accuracy, while
for the second dataset, MobileNetV2 has performed best with an accuracy of 81%.
KEYWORDS
artificial intelligence, chest X-rays, COVID-19, deep learning, transfer learning
1 | INTRODUCTION
The year 2020 was marked by a continuing pandemic that was first detected in Wuhan, China, at the end of December 2019 (Wang et al., 2020).
As recorded on 18th July 2020, there have been 1,40,60,402 infected cases causing 6,01,820 deaths worldwide (Worldometer, 2020). COVID-19
is caused by a coronavirus named SARS-Cov-2, which belongs to the β-coronavirus family. This virus is highly transmissible compared to viruses
causing Middle East respiratory syndrome (MERS) and severe acute respiratory syndrome (SARS), namely MERS-Cov and SARS-Cov. Analysis of
Received: 12 April 2021 Revised: 9 May 2021 Accepted: 23 May 2021
DOI: 10.1111/exsy.12749
Expert Systems. 2021;e12749. wileyonlinelibrary.com/journal/exsy © 2021 John Wiley & Sons Ltd. 1 of 17
https://doi.org/10.1111/exsy.12749