Fine Tuning CNN for COVID-19 Patterns Detection From Chest Radiographs

Fine Tuning CNN for COVID-19 Patterns Detection From Chest Radiographs

Anju Jain, Saroj Ratnoo, Dinesh Kumar
Copyright: © 2022 |Pages: 15
DOI: 10.4018/IJRQEH.308801
Article PDF Download
Open access articles are freely available for download

Abstract

The COVID-19 pandemic has crumbled health systems all over the world. Quick and accurate detection of coronavirus infection plays an important role in timely referral of physicians and control transmission of the disease. RT-PCR is the most widely test used for identification of COVID-19 patients, but it takes long to deliver the report. Researchers around the world are looking for alternative machine learning techniques including deep learning to assist the medical experts for early COVID-19 disease diagnosis from medical imaging such as chest films. This study proposes an enhanced convolutional neural network (EConvNet) model for the presence and absence of coronavirus disease from chest radiographs to contain this pandemic. The model is accurate compared to the traditional machine learning algorithms (RF, SVM, etc.). The suggested CNN model is approximately as accurate as the classifiers based on transfer learning (such as InceptionV3, VGG16, and Densenet121). Despite being simple in terms of number of parameters learnt, it takes less training time and demands less memory.
Article Preview
Top

Background

Since CNN has shown promising results for classification tasks, the authors have used CNN for Covid-19 disease diagnosis and compared its performance with state-of-the art deep transfer learning models in this paper. Description of CNN and transfer learning is as follows.

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