Very Deep Convolutional Networks based transfer learning approach for SARS-CoV-2 recognition from chest CT images
DOI:
https://doi.org/10.62110/sciencein.jist.2025.v13.1009Keywords:
Artificial Intelligence, Chest tomography, Computed Tomography, Convolutional Neural Network (CNN), VGG-19, Covid-19, Viral InfectionAbstract
After COVID-19 epidemic globe is now experiencing a health catastrophe that is unprecedented in its epidemic. Scholars are worried about seeking solutions to halt the international health crisis and preserve lives as the coronavirus spreads. The issues brought on by pandemics have been addressed partly through adopting AI in this paper. Stacked CNN above VGG-19 constructs an AI system to recognize coronavirus from chest tomography pictures and extract characteristics from the images. An expanded dataset, formulated by combining chest images from coronavirus cases with typical chest tomography scans accessed from public resources, has been fine-tuned on two potent networks, namely CNN and VGG19. The findings provide excellent performance and simple global spread recognition strategies, providing evidence for the effectiveness of transfer learning.98% accuracy of VGG-19 model with stacked CNN. Accurately automate the process of interpreting CT pictures, and it may also be used when there are few materials and RT-PCR tests.
Downloads
Downloads
Published
Issue
Section
URN
License
Copyright (c) 2024 Namrata Nikam, Sanjay Ganorkar, Vrushali Raut
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Rights and Permission