Citation: Furtado, A.; Andrade, L.;
Frias, D.; Maia, T.; Badaró, R.;
Nascimento, E.G.S. Deep Learning
Applied to Chest Radiograph
Classification—A COVID-19
Pneumonia Experience. Appl. Sci.
2022, 12, 3712. https://doi.org/
10.3390/app12083712
Academic Editors: Keun Ho Ryu and
Nipon Theera-Umpon
Received: 25 February 2022
Accepted: 4 April 2022
Published: 7 April 2022
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2022 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
Article
Deep Learning Applied to Chest Radiograph Classification—A
COVID-19 Pneumonia Experience
Adhvan Furtado
1
, Leandro Andrade
2
, Diego Frias
3
, Thiago Maia
4
, Roberto Badaró
5
and Erick G. Sperandio Nascimento
1,
*
1
Super Computing Center SENAI/CIMATEC, Av. Orlando Gomes, 1845, Piatã, Salvador 41560-010, Brazil;
adhvan@fieb.org.br
2
Escola de Administração, Universidade Federal da Bahia, Avenida Reitor Miguel Calmon s/n Vale do-Canela,
Salvador 40110-903, Brazil; leandrojsa@ufba.br
3
Department of Natural and Earth Sciences, Universidade do Estado da Bahia, Rua Silveira Martins, 2555,
Cabula 41150-000, Brazil; diegofrias@uneb.br
4
SAMEDIL—Serviços de Atendimento Médico, Rua Pedro Fonseca, 170-Monte Belo, Vitória 29053-280, Brazil;
thiago.maia@medsenior.com.br
5
Instituto SENAI de Inovação em Saúde, Av. Orlando Gomes, 1845, Piatã, Salvador 41560-010, Brazil;
badaro@fieb.org.br
* Correspondence: erick.sperandio@fieb.org.br; Tel.: +55-27-992-799-651
Featured Application: The open-source deep learning algorithm presented in this work can iden-
tify anomalous chest radiographs and support the detection of COVID-19 cases. It is a comple-
mentary tool to support COVID-19 identification in areas with no access to radiology special-
ists or RT-PCR tests. We encourage the use of the algorithm to support COVID-19 screening,
for educational purposes, as a baseline for further enhancements, and as a benchmark for differ-
ent solutions. The algorithm is currently being tested in clinical practice in a hospital in Espírito
Santo, Brazil.
Abstract:
Due to the recent COVID-19 pandemic, a large number of reports present deep learning
algorithms that support the detection of pneumonia caused by COVID-19 in chest radiographs.
Few studies have provided the complete source code, limiting testing and reproducibility on different
datasets. This work presents Cimatec_XCOV19, a novel deep learning system inspired by the
Inception-V3 architecture that is able to (i) support the identification of abnormal chest radiographs
and (ii) classify the abnormal radiographs as suggestive of COVID-19. The training dataset has
44,031 images with 2917 COVID-19 cases, one of the largest datasets in recent literature. We organized
and published an external validation dataset of 1158 chest radiographs from a Brazilian hospital.
Two experienced radiologists independently evaluated the radiographs. The Cimatec_XCOV19
algorithm obtained a sensitivity of 0.85, specificity of 0.82, and AUC ROC of 0.93. We compared
the AUC ROC of our algorithm with a well-known public solution and did not find a statistically
relevant difference between both performances. We provide full access to the code and the test
dataset, enabling this work to be used as a tool for supporting the fast screening of COVID-19 on chest
X-ray exams, serving as a reference for educators, and supporting further algorithm enhancements.
Keywords: deep learning; COVID-19; chest radiograph
1. Introduction
The exponential spread of COVID-19 in the world poses substantial challenges for
public health services. The disease, caused by the severe acute respiratory syndrome coron-
avirus 2 (SARS-CoV-2), initially identified in December 2019 in Wuhan, China, causes respi-
ratory tract infections and spreads rapidly through contagion between people, thus overbur-
dening health systems worldwide. It is necessary to evaluate the contagion scenarios and
Appl. Sci. 2022, 12, 3712. https://doi.org/10.3390/app12083712 https://www.mdpi.com/journal/applsci
