ResearchArticle
ADA-COVID: Adversarial Deep Domain Adaptation-Based
DiagnosisofCOVID-19fromLungCTScansUsing
Triplet Embeddings
Mehrad Aria ,
1
Esmaeil Nourani ,
1
andAminGolzariOskouei
2
1
Faculty of Information Technology and Computer Engineering, Azarbaijan Shahid Madani University, Tabriz, Iran
2
Department of Computer Engineering, Faculty of Electrical and Computer Engineering, University of Tabriz, Tabriz, Iran
Correspondence should be addressed to Esmaeil Nourani; ac.nourani@azaruniv.ac.ir
Received 13 November 2021; Revised 8 December 2021; Accepted 7 January 2022; Published 8 February 2022
Academic Editor: Jianli Liu
Copyright©2022MehradAriaetal.isisanopenaccessarticledistributedundertheCreativeCommonsAttributionLicense,
which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
RapiddiagnosisofCOVID-19withhighreliabilityisessentialintheearlystages.Tothisend,recentresearchoftenusesmedical
imaging combined with machine vision methods to diagnose COVID-19. However, the scarcity of medical images and the
inherent differences in existing datasets that arise from different medical imaging tools, methods, and specialists may affect the
generalization of machine learning-based methods. Also, most of these methods are trained and tested on the same dataset,
reducingthegeneralizabilityandcausinglowreliabilityoftheobtainedmodelinreal-worldapplications.ispaperintroducesan
adversarialdeepdomainadaptation-basedapproachfordiagnosingCOVID-19fromlungCTscanimages,termedADA-COVID.
Domainadaptation-basedtrainingprocessreceivesmultipledatasetswithdifferentinputdomainstogeneratedomain-invariant
representations for medical images. Also, due to the excessive structural similarity of medical images compared to other image
data in machine vision tasks, we use the triplet loss function to generate similar representations for samples of the same class
(infected cases). e performance of ADA-COVID is evaluated and compared with other state-of-the-art COVID-19 diagnosis
algorithms. e obtained results indicate that ADA-COVID achieves classification improvements of at least 3%, 20%, 20%, and
11% in accuracy, precision, recall, and F
1
score, respectively, compared to the best results of competitors, even without directly
training on the same data. e implementation source code of the ADA-COVID is publicly available at https://github.com/
MehradAria/ADA-COVID.
1.Introduction
Nearly 268 million people worldwide officially have been
infected with the COVID-19, and more than 5.2 million
death tolls until November 2021 [1] as of epidemic decla-
ration in March 2020 signify the rapid diagnosis of the
COVID-19 with high reliability in the early stages, not only
to save human lives but also to reduce the social and eco-
nomic burden on the communities involved. Although the
RT-PCR (real-time polymerase chain reaction) test is the
standard reference for confirming COVID-19, some studies
showthatthislaboriousmethodcannotdiagnosethedisease
in the early stages [2–5], and some studies report a high
false-negative rate [6].
One standard way to identify morphological patterns of
lung lesions associated with COVID-19 is to use chest scan
images.erearetwocommontechniquesforscanningthe
chest: X-rays and computer tomography (CT). Detection of
COVID-19 from chest images by a radiologist is time-
consuming, and the accuracy of COVID-19 diagnosis de-
pends strongly on the radiologist’s opinion [7, 8]. Also,
manually checking every image might not be feasible in
emergency cases. Recently, deep learning-based methods
[9, 10] have been applied to help the medical community
diagnose COVID-19 quickly, accurately, and automatically.
Using CT images to diagnose COVID-19 has recently
drawn researchers’ interest due to some key ideas that they
possess: more accurate images of bones, organs, blood
Hindawi
Computational Intelligence and Neuroscience
Volume 2022, Article ID 2564022, 17 pages
https://doi.org/10.1155/2022/2564022