Viruses 2022, 14, 1667. https://doi.org/10.3390/v14081667 www.mdpi.com/journal/viruses
Article
Novel Coronavirus and Common Pneumonia Detection from
CT Scans Using Deep Learning-Based Extracted Features
Ghazanfar Latif
1,2,
*, Hamdy Morsy
3,4
, Asmaa Hassan
5
and Jaafar Alghazo
6
1
Computer Science Department, Prince Mohammad Bin Fahd University, Khobar 34754, Saudi Arabia
2
Department of Computer Sciences and Mathematics, Université du Québec à Chicoutimi,
555 Boulevard de l’Université, Chicoutimi, QC G7H 2B1, Canada
3
Department of Applied Natural Sciences, College of Community, Qassim University,
Buraydah 52571, Saudi Arabia; h.morsy@qu.edu.sa
4
Department of Electronics and communications, College of Engineering, Helwan University,
Cairo 11792, Egypt
5
Faculty of Medicine, Helwan University, Helwan 11795, Egypt; asmaa49eg@gmail.com
6
Department of Electrical and Computer Engineering, Virginia Military Institute, Lexington, VA 24450, USA;
alghazojm@vmi.edu
* Correspondence: ghazanfar.latif1@uqac.ca or glatif@pmu.edu.sa
Abstract: COVID-19 which was announced as a pandemic on 11 March 2020, is still infecting mil-
lions to date as the vaccines that have been developed do not prevent the disease but rather reduce
the severity of the symptoms. Until a vaccine is developed that can prevent COVID-19 infection, the
testing of individuals will be a continuous process. Medical personnel monitor and treat all health
conditions; hence, the time-consuming process to monitor and test all individuals for COVID-19
becomes an impossible task, especially as COVID-19 shares similar symptoms with the common
cold and pneumonia. Some off-the-counter tests have been developed and sold, but they are unre-
liable and add an additional burden because false-positive cases have to visit hospitals and perform
specialized diagnostic tests to confirm the diagnosis. Therefore, the need for systems that can auto-
matically detect and diagnose COVID-19 automatically without human intervention is still an ur-
gent priority and will remain so because the same technology can be used for future pandemics and
other health conditions. In this paper, we propose a modified machine learning (ML) process that
integrates deep learning (DL) algorithms for feature extraction and well-known classifiers that can
accurately detect and diagnose COVID-19 from chest CT scans. Publicly available datasets were
made available by the China Consortium for Chest CT Image Investigation (CC-CCII). The highest
average accuracy obtained was 99.9% using the modified ML process when 2000 features were ex-
tracted using GoogleNet and ResNet18 and using the support vector machine (SVM) classifier. The
results obtained using the modified ML process were higher when compared to similar methods
reported in the extant literature using the same datasets or different datasets of similar size; thus,
this study is considered of added value to the current body of knowledge. Further research in this
field is required to develop methods that can be applied in hospitals and can better equip mankind
to be prepared for any future pandemics.
Keywords: chest CT scan; COVID-19 detection; deep learning features; convolutional neural
network (CNN); common pneumonia; novel coronavirus pneumonia
1. Introduction
The World Health Organization (WHO) announced the Severe Acute Respiratory
Syndrome Coronavirus 2 (SARS-CoV-2) as a pandemic on 11 March 2020. The first re-
ported case was in December 2019; due to the contagious nature of the virus, it started to
spread all over the world. SARS-CoV-2, which gives rise to Coronavirus Disease 19
(COVID-19), is a type of coronavirus that causes diseases in mammals and birds. COVID-
Citation: Latif, G.; Morsy, H.;
Hassan, A.; Alghazo, J. Novel
Coronavirus and Common
Pneumonia Detection from CT Scans
Using Deep Learning-Based
Extracted Features. Viruses 2022, 14,
1667. https://doi.org/10.3390/
v14081667
Academic Editor: Donald Seto
Received: 25 June 2022
Accepted: 26 July 2022
Published: 28 July 2022
Publisher’s Note: MDPI stays neu-
tral with regard to jurisdictional
claims in published maps and institu-
tional affiliations.
Copyright: © 2022 by the authors. Li-
censee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and con-
ditions of the Creative Commons At-
tribution (CC BY) license (https://cre-
ativecommons.org/licenses/by/4.0/).