A Two-Stage Method for Diagnosing COVID-19, Leveraging CNN, and Transfer Learning on CT Scan Images

Lung infection represents one of the most perilous indicators of Covid-19. The most efficient diagnostic approach entails the analysis of CT scan images. Utilizing deep learning algorithms and machine vision, computer scientists have devised a method for automated detection of this disease. This stu...

Full description

Saved in:
Bibliographic Details
Main Authors: Touba torabipour, Abolfazl Gandomi, Mohammad Ghanimi
Format: Article
Language:English
Published: University of science and culture 2023-07-01
Series:International Journal of Web Research
Subjects:
Online Access:https://ijwr.usc.ac.ir/article_197180_ca24efdc59c110e9cfdd5830269b4608.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846107911838760960
author Touba torabipour
Abolfazl Gandomi
Mohammad Ghanimi
author_facet Touba torabipour
Abolfazl Gandomi
Mohammad Ghanimi
author_sort Touba torabipour
collection DOAJ
description Lung infection represents one of the most perilous indicators of Covid-19. The most efficient diagnostic approach entails the analysis of CT scan images. Utilizing deep learning algorithms and machine vision, computer scientists have devised a method for automated detection of this disease. This study proposes a two-stage approach to identifying lung infection. In the initial stage, image features are extracted through a transfer learning framework employing ResNet50, with the last two layers being fixed. Subsequently, a CNN neural network is constructed for image detection and categorization in the second stage. By employing superior image feature selection and minimizing non-informative features, this proposed method achieves impressive accuracy metrics: 98.99% accuracy, 98.91% sensitivity, and 99.10% specificity. Furthermore, a comparative analysis is conducted between this method and six other architectures (Inception, InceptionResNetV2, ResNet101, ResNet152, VGG16, VGG19), with and without transfer learning. The findings demonstrate that the proposed method attains 98% accuracy on test data, without succumbing to overfitting.
format Article
id doaj-art-227bf38e762a44e2b1df5d472b204ba1
institution Kabale University
issn 2645-4343
language English
publishDate 2023-07-01
publisher University of science and culture
record_format Article
series International Journal of Web Research
spelling doaj-art-227bf38e762a44e2b1df5d472b204ba12024-12-26T08:02:06ZengUniversity of science and cultureInternational Journal of Web Research2645-43432023-07-016213314210.22133/ijwr.2024.449726.1211A Two-Stage Method for Diagnosing COVID-19, Leveraging CNN, and Transfer Learning on CT Scan ImagesTouba torabipour0Abolfazl Gandomi 1Mohammad Ghanimi2Department of Computer, Yazd Branch, Islamic Azad University, Yazd, IranDepartment of Computer, Yazd Branch, Islamic Azad University, Yazd, IranDepartment of Computer, Ershad Damavand University, Tehran, IranLung infection represents one of the most perilous indicators of Covid-19. The most efficient diagnostic approach entails the analysis of CT scan images. Utilizing deep learning algorithms and machine vision, computer scientists have devised a method for automated detection of this disease. This study proposes a two-stage approach to identifying lung infection. In the initial stage, image features are extracted through a transfer learning framework employing ResNet50, with the last two layers being fixed. Subsequently, a CNN neural network is constructed for image detection and categorization in the second stage. By employing superior image feature selection and minimizing non-informative features, this proposed method achieves impressive accuracy metrics: 98.99% accuracy, 98.91% sensitivity, and 99.10% specificity. Furthermore, a comparative analysis is conducted between this method and six other architectures (Inception, InceptionResNetV2, ResNet101, ResNet152, VGG16, VGG19), with and without transfer learning. The findings demonstrate that the proposed method attains 98% accuracy on test data, without succumbing to overfitting.https://ijwr.usc.ac.ir/article_197180_ca24efdc59c110e9cfdd5830269b4608.pdfnatural networkconvolutiondeep learningcovid 19ct scan radiographs
spellingShingle Touba torabipour
Abolfazl Gandomi
Mohammad Ghanimi
A Two-Stage Method for Diagnosing COVID-19, Leveraging CNN, and Transfer Learning on CT Scan Images
International Journal of Web Research
natural network
convolution
deep learning
covid 19
ct scan radiographs
title A Two-Stage Method for Diagnosing COVID-19, Leveraging CNN, and Transfer Learning on CT Scan Images
title_full A Two-Stage Method for Diagnosing COVID-19, Leveraging CNN, and Transfer Learning on CT Scan Images
title_fullStr A Two-Stage Method for Diagnosing COVID-19, Leveraging CNN, and Transfer Learning on CT Scan Images
title_full_unstemmed A Two-Stage Method for Diagnosing COVID-19, Leveraging CNN, and Transfer Learning on CT Scan Images
title_short A Two-Stage Method for Diagnosing COVID-19, Leveraging CNN, and Transfer Learning on CT Scan Images
title_sort two stage method for diagnosing covid 19 leveraging cnn and transfer learning on ct scan images
topic natural network
convolution
deep learning
covid 19
ct scan radiographs
url https://ijwr.usc.ac.ir/article_197180_ca24efdc59c110e9cfdd5830269b4608.pdf
work_keys_str_mv AT toubatorabipour atwostagemethodfordiagnosingcovid19leveragingcnnandtransferlearningonctscanimages
AT abolfazlgandomi atwostagemethodfordiagnosingcovid19leveragingcnnandtransferlearningonctscanimages
AT mohammadghanimi atwostagemethodfordiagnosingcovid19leveragingcnnandtransferlearningonctscanimages
AT toubatorabipour twostagemethodfordiagnosingcovid19leveragingcnnandtransferlearningonctscanimages
AT abolfazlgandomi twostagemethodfordiagnosingcovid19leveragingcnnandtransferlearningonctscanimages
AT mohammadghanimi twostagemethodfordiagnosingcovid19leveragingcnnandtransferlearningonctscanimages