Abstract

Coronavirus disease (COVID-19) is a pandemic disease, which has already\ncaused thousands of causalities and infected several millions of people\nworldwide. Any technological tool enabling rapid screening of the COVID-19\ninfection with high accuracy can be crucially helpful to healthcare\nprofessionals. The main clinical tool currently in use for the diagnosis of\nCOVID-19 is the Reverse transcription polymerase chain reaction (RT-PCR), which\nis expensive, less-sensitive and requires specialized medical personnel. X-ray\nimaging is an easily accessible tool that can be an excellent alternative in\nthe COVID-19 diagnosis. This research was taken to investigate the utility of\nartificial intelligence (AI) in the rapid and accurate detection of COVID-19\nfrom chest X-ray images. The aim of this paper is to propose a robust technique\nfor automatic detection of COVID-19 pneumonia from digital chest X-ray images\napplying pre-trained deep-learning algorithms while maximizing the detection\naccuracy. A public database was created by the authors combining several public\ndatabases and also by collecting images from recently published articles. The\ndatabase contains a mixture of 423 COVID-19, 1485 viral pneumonia, and 1579\nnormal chest X-ray images. Transfer learning technique was used with the help\nof image augmentation to train and validate several pre-trained deep\nConvolutional Neural Networks (CNNs). The networks were trained to classify two\ndifferent schemes: i) normal and COVID-19 pneumonia; ii) normal, viral and\nCOVID-19 pneumonia with and without image augmentation. The classification\naccuracy, precision, sensitivity, and specificity for both the schemes were\n99.7%, 99.7%, 99.7% and 99.55% and 97.9%, 97.95%, 97.9%, and 98.8%,\nrespectively.\n

Keywords

Coronavirus disease 2019 (COVID-19)PneumoniaViral pneumoniaVirologySevere acute respiratory syndrome coronavirus 2 (SARS-CoV-2)2019-20 coronavirus outbreakComputer scienceMedicineOutbreakInternal medicineInfectious disease (medical specialty)

Affiliated Institutions

Related Publications

Publication Info

Year
2020
Type
article
Volume
8
Pages
132665-132676
Citations
1819
Access
Closed

External Links

Social Impact

Social media, news, blog, policy document mentions

Citation Metrics

1819
OpenAlex

Cite This

Muhammad E. H. Chowdhury, Tawsifur Rahman, Amith Khandakar et al. (2020). Can AI Help in Screening Viral and COVID-19 Pneumonia?. IEEE Access , 8 , 132665-132676. https://doi.org/10.1109/access.2020.3010287

Identifiers

DOI
10.1109/access.2020.3010287