Detection of COVID-19 using deep learning on x-ray lung images.
PeerJ Comput Sci
; 8: e1082, 2022.
Article
in English
| MEDLINE | ID: covidwho-2080856
ABSTRACT
COVID-19 is a widespread deadly virus that directly affects the human lungs. The spread of COVID-19 did not stop at humans but also reached animals, so it was necessary to limit it is spread and diagnose cases quickly by applying a quarantine to the infected people. Recently x-ray lung images are used to determine the infection and from here the idea of this research came to use deep learning techniques to analyze x-ray lung images publicly available on Kaggle to possibly detect COVID-19 infection. In this article, we have proposed a method to possibly detect the COVID-19 by analyzing the X-ray images and applying a number of deep learning pre-trained models such as InceptionV3, DenseNet121, ResNet50, and VGG16, and the results are compared to determine the best performance model and accuracy with the least loss for our dataset. Our evaluation results showed that the best performing model for our dataset is ResNet50 with accuracies of 99.99%, 99.50%, and 99.44% for training, validation, and testing respectively followed by DenseNet121, InceptionV3, and finally VGG16.
Full text:
Available
Collection:
International databases
Database:
MEDLINE
Type of study:
Experimental Studies
/
Prognostic study
Language:
English
Journal:
PeerJ Comput Sci
Year:
2022
Document Type:
Article
Affiliation country:
PEERJ-CS.1082
Similar
MEDLINE
...
LILACS
LIS