Diagnosis of COVID-19 disease based on a modified convolutional neural network on the example of lung X-rays
|
Full Text |
Pdf
|
|
Author |
I. Fedorchenko, A. Oliinyk, J. A. J. Alsayaydeh, A. Stepanenko, T. Fedoronchak, S. Korniienko and M. Chornobuk
|
|
e-ISSN |
1819-6608 |
|
On Pages
|
1337-1344
|
|
Volume No. |
18
|
|
Issue No. |
11
|
|
Issue Date |
August 13, 2023
|
|
DOI |
https://doi.org/10.59018/0623171
|
|
Keywords |
pattern recognition, COVID-19, classification, neural network, perceptron.
|
Abstract
As a result of the study, a machine learning model based on a modified convolutional neural network was developed to diagnose COVID-19 lesions from lung X-rays. Due to the improvement of the network architecture, it was possible to obtain a classification accuracy of 91%. The developed model can be used in the field of health care to assist medical staff in the analysis of X-rays, which will reduce the likelihood of medical error.
Back