The impact of super resolution on detecting COVID-19 from CT scans using VGG-16 based learning

N. Aburaed; A. Panthakkan; M. Al-Saad; S. Al Mansoori; Hussain Al Ahmad

doi:10.1088/1742-6596/1828/1/012009

The impact of super resolution on detecting COVID-19 from CT scans using VGG-16 based learning

N. Aburaed^*, A. Panthakkan, M. Al-Saad, S. Al Mansoori, Hussain Al Ahmad

^*Corresponding author for this work

Electronic And Electrical Engineering

Research output: Contribution to journal › Conference article › peer-review

2 Citations (Scopus)

27 Downloads (Pure)

Abstract

With the recent outbreak of the novel Coronavirus (COVID-19), the importance of early and accurate diagnosis arises, as it directly affects mortality rates. Computed Tomography (CT) scans of the patients’ lungs is one of the diagnosis methods utilized in some countries, such as China. Manual inspection of CT scans can be a lengthy process, and may lead to inaccurate diagnosis. In this paper, a Deep Learning strategy based on VGG-16 is utilized with Transfer Learning for the purpose of binary classification of CT scans; Covid and NonCovid. Additionally, it is hypothesized in this study that Single Image Super Resolution (SISR) can boost the accuracy of the networks’ performance. This hypothesis is tested by following the training strategy with the original dataset as well as the same dataset scaled by a factor of ×2. Experimental results show that SISR has a positive effect on the overall training performance.

Original language	English
Article number	012009
Journal	Journal of Physics: Conference Series
Volume	1828
Issue number	1
DOIs	https://doi.org/10.1088/1742-6596/1828/1/012009
Publication status	Published - 4 Mar 2021
Event	2020 International Symposium on Automation, Information and Computing, ISAIC 2020 - Beijing, Virtual, China Duration: 2 Dec 2020 → 4 Dec 2020

Keywords

Computed Tomography (CT)
COVID-19
Coronavirus
Single Image Super Resolution (SISR)
deep learning

Access to Document

10.1088/1742-6596/1828/1/012009Licence: CC BY 4.0

Aburaed-etal-JoP-2021-The-impact-of-super-resolution-on-detecting-COVID-19-from-CT-scanFinal published version, 410 KBLicence: CC BY 3.0

Cite this

@article{8b8e540b075d45d2bb9dc05ff261cb86,

title = "The impact of super resolution on detecting COVID-19 from CT scans using VGG-16 based learning",

abstract = "With the recent outbreak of the novel Coronavirus (COVID-19), the importance of early and accurate diagnosis arises, as it directly affects mortality rates. Computed Tomography (CT) scans of the patients{\textquoteright} lungs is one of the diagnosis methods utilized in some countries, such as China. Manual inspection of CT scans can be a lengthy process, and may lead to inaccurate diagnosis. In this paper, a Deep Learning strategy based on VGG-16 is utilized with Transfer Learning for the purpose of binary classification of CT scans; Covid and NonCovid. Additionally, it is hypothesized in this study that Single Image Super Resolution (SISR) can boost the accuracy of the networks{\textquoteright} performance. This hypothesis is tested by following the training strategy with the original dataset as well as the same dataset scaled by a factor of ×2. Experimental results show that SISR has a positive effect on the overall training performance.",

keywords = "Computed Tomography (CT), COVID-19, Coronavirus, Single Image Super Resolution (SISR), deep learning",

author = "N. Aburaed and A. Panthakkan and M. Al-Saad and {Al Mansoori}, S. and Ahmad, {Hussain Al}",

year = "2021",

month = mar,

day = "4",

doi = "10.1088/1742-6596/1828/1/012009",

language = "English",

volume = "1828",

journal = "Journal of Physics: Conference Series",

issn = "1742-6588",

number = "1",

note = "2020 International Symposium on Automation, Information and Computing, ISAIC 2020 ; Conference date: 02-12-2020 Through 04-12-2020",

}

TY - JOUR

T1 - The impact of super resolution on detecting COVID-19 from CT scans using VGG-16 based learning

AU - Aburaed, N.

AU - Panthakkan, A.

AU - Al-Saad, M.

AU - Al Mansoori, S.

AU - Ahmad, Hussain Al

PY - 2021/3/4

Y1 - 2021/3/4

N2 - With the recent outbreak of the novel Coronavirus (COVID-19), the importance of early and accurate diagnosis arises, as it directly affects mortality rates. Computed Tomography (CT) scans of the patients’ lungs is one of the diagnosis methods utilized in some countries, such as China. Manual inspection of CT scans can be a lengthy process, and may lead to inaccurate diagnosis. In this paper, a Deep Learning strategy based on VGG-16 is utilized with Transfer Learning for the purpose of binary classification of CT scans; Covid and NonCovid. Additionally, it is hypothesized in this study that Single Image Super Resolution (SISR) can boost the accuracy of the networks’ performance. This hypothesis is tested by following the training strategy with the original dataset as well as the same dataset scaled by a factor of ×2. Experimental results show that SISR has a positive effect on the overall training performance.

AB - With the recent outbreak of the novel Coronavirus (COVID-19), the importance of early and accurate diagnosis arises, as it directly affects mortality rates. Computed Tomography (CT) scans of the patients’ lungs is one of the diagnosis methods utilized in some countries, such as China. Manual inspection of CT scans can be a lengthy process, and may lead to inaccurate diagnosis. In this paper, a Deep Learning strategy based on VGG-16 is utilized with Transfer Learning for the purpose of binary classification of CT scans; Covid and NonCovid. Additionally, it is hypothesized in this study that Single Image Super Resolution (SISR) can boost the accuracy of the networks’ performance. This hypothesis is tested by following the training strategy with the original dataset as well as the same dataset scaled by a factor of ×2. Experimental results show that SISR has a positive effect on the overall training performance.

KW - Computed Tomography (CT)

KW - COVID-19

KW - Coronavirus

KW - Single Image Super Resolution (SISR)

KW - deep learning

U2 - 10.1088/1742-6596/1828/1/012009

DO - 10.1088/1742-6596/1828/1/012009

M3 - Conference article

AN - SCOPUS:85103269188

SN - 1742-6588

VL - 1828

JO - Journal of Physics: Conference Series

JF - Journal of Physics: Conference Series

IS - 1

M1 - 012009

T2 - 2020 International Symposium on Automation, Information and Computing, ISAIC 2020

Y2 - 2 December 2020 through 4 December 2020

ER -

The impact of super resolution on detecting COVID-19 from CT scans using VGG-16 based learning

Abstract

Keywords

Access to Document

Fingerprint

Cite this