Diagnosing COVID-19 From Chest CT Scan Images Using Deep Learning Models

Diagnosing COVID-19 From Chest CT Scan Images Using Deep Learning Models

Shamik Tiwari, Anurag Jain, Sunil Kumar Chawla
Copyright: © 2022 |Pages: 15
DOI: 10.4018/IJRQEH.299961
Article PDF Download
Open access articles are freely available for download

Abstract

A novel coronavirus named COVID-19 has spread speedily and has triggered a worldwide outbreak of respiratory illness. Early diagnosis is always crucial for pandemic control. Compared to RT-PCR, chest computed tomography (CT) imaging is the more consistent, concrete, and prompt method to identify COVID-19 patients. For clinical diagnostics, the information received from computed tomography scans is critical. So there is a need to develop an image analysis technique for detecting viral epidemics from computed tomography scan pictures. Using DenseNet, ResNet, CapsNet, and 3D-ConvNet, four deep machine learning-based architectures have been proposed for COVID-19 diagnosis from chest computed tomography scans. From the experimental results, it is found that all the architectures are providing effective accuracy, of which the COVID-DNet model has reached the highest accuracy of 99%. Proposed architectures are accessible at https://github.com/shamiktiwari/CTscanCovi19 can be utilized to support radiologists and reserachers in validating their initial screening.
Article Preview
Top

Introduction

A global pandemic has been resulting from the IJRQEH.299961.m01 virus, which was detected in November 2019. This virus shares genetic similarities with the SARS virus, which was discovered in 2002. This virus was created in bats and then transmitted to humans through them (Jahangir et al., 2020). This virus can spread via the air through water droplets released by affected people while sneezing, speaking, or coughing, and can be active for up to three hours (Alpaydin et al., 2021). The virus is also capable of surviving on the surfaces of objects for a very long time (Bhardwaj et al., 2021). IJRQEH.299961.m02 is more common in people over 60, children under the age of 12, asthmatic patients, people with weakened immune systems, and pregnant women. The earliest signs of IJRQEH.299961.m03 are a high temperature, exhaustion, low breath, cough, loss of aroma and flavor. Later on, this progresses to serious lung damage, which is referred to as acute respiratory distress syndrome in medical terms (ARDS). After five days of infection, a person develops IJRQEH.299961.m04 symptoms. The incubation period is five days, and during this time, a IJRQEH.299961.m05 affected individual becomes a moving source of infection (Jain et al., 2021). At the moment, one individual affected with IJRQEH.299961.m06 is infecting another 2.2 people. A doctor can utilize the RT-PCR test to confirm the condition. This method can also identify a trace amount of viral ribonucleic acid (RNA). At the initial stage, however, this test fails to identify the IJRQEH.299961.m07 virus (Tahamtan & Ardebili, 2020). A clinician can diagnose lung disease resulting from IJRQEH.299961.m08 infection utilizing chest CT (Computed Tomography) scans. Other approaches for detecting IJRQEH.299961.m09 include serological testing. This approach looks for antibodies produced by the immune system to attack the virus to determine the presence of the IJRQEH.299961.m1019 virus (Lee et al., 2020). The sensitivity of the RT-PCR test was between 30 and 70% at the start of the pandemic. The sensitivity of the second generation RT-PCR test has increased to 95%, making it more accurate than a chest x-ray. However, the RT-PCR test still has issues with waiting times, test costs, and the lack of testing facilities worldwide.

Complete Article List

Search this Journal:
Reset
Volume 13: 1 Issue (2024): Forthcoming, Available for Pre-Order
Volume 12: 2 Issues (2023)
Volume 11: 4 Issues (2022)
Volume 10: 4 Issues (2021)
Volume 9: 4 Issues (2020)
Volume 8: 4 Issues (2019)
Volume 7: 4 Issues (2018)
Volume 6: 4 Issues (2017)
Volume 5: 4 Issues (2016)
Volume 4: 4 Issues (2015)
Volume 3: 4 Issues (2014)
Volume 2: 4 Issues (2013)
Volume 1: 4 Issues (2012)
View Complete Journal Contents Listing