Volume 20 No 22 (2022)
 Download PDF
MATHEMATICAL EVALUATION OF COVID-19 DETECTION TECHNIQUE USING CXR RADIOGRAPHS OF PATIENTS, USING DENSENET-201
José Allauca P
Abstract
A current COVID-19 detection tool is CXR imaging, which has been developing since 2019 to provide early diagnosis; it can be performed in any health unit and is more affordable than Real Time Polymerase Chain Reaction (RT-PCR) tests. However, diagnosis with Chest X Ray (CXR) images had not achieved the predictive capacity required to replace the RT-PCR test; previous studies with a limited number of images have evaluated their models. This research seeks to contribute to the detection of COVID-19 from CXR images, with the evaluation of a convolutional neural network model from CXR images, through the use of open source code on a free dataset of approximately 30 thousand images. The algorithm and mathematical model used was DenseNet-201. The results of the experiment show a precision and accuracy of more than 95% and specificity, sensitivity, predictive ability and F1 measurement of more than 90%.
Keywords
COVID-19; CNN; CXR; Image Classification.
Copyright
Copyright © Neuroquantology

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Articles published in the Neuroquantology are available under Creative Commons Attribution Non-Commercial No Derivatives Licence (CC BY-NC-ND 4.0). Authors retain copyright in their work and grant IJECSE right of first publication under CC BY-NC-ND 4.0. Users have the right to read, download, copy, distribute, print, search, or link to the full texts of articles in this journal, and to use them for any other lawful purpose.