Author: Jullapak, R.; Yampaka, T.
Title: COVID-19 Classification using DCNNs and Exploration Correlation using Canonical Correlation Analysis Cord-id: oldtbm5e Document date: 2021_1_1
ID: oldtbm5e
Snippet: Coronavirus disease (COVID-19) has rapidly spread among people living in many countries. Chest radiography (CXR) image is an alternative diagnosis option to observe COVID-19. However, CXR usually requires an expert radiologist to distinguish the lesion from viral pneumonia and COVID-19 because the symptoms of COVID-19 pneumonia may be similar to other types of viral pneumonia. In this study, three different convolutional neural network based models (VGG19, ResNet50, and InceptionV3) have been pr
Document: Coronavirus disease (COVID-19) has rapidly spread among people living in many countries. Chest radiography (CXR) image is an alternative diagnosis option to observe COVID-19. However, CXR usually requires an expert radiologist to distinguish the lesion from viral pneumonia and COVID-19 because the symptoms of COVID-19 pneumonia may be similar to other types of viral pneumonia. In this study, three different convolutional neural network based models (VGG19, ResNet50, and InceptionV3) have been proposed for the detection of coronavirus pneumonia infected patient using chest X-ray. In addition, this studies can potentially find the correlation between COVID-19 pneumonia and viral pneumonia using canonical correlation analysis. Considering the performance results obtained the best performance as an accuracy of 0.97, sensitivity of 0.97, specificity of 0.93, and F1-score value of 0.97 for VGG19 pre-trained model. The experiment results also show that the viral lesion of Viral pneumonia and COVID-19 is less similarity. © 2021 IEEE.
Search related documents:
Co phrase search for related documents- Try single phrases listed below for: 1
Co phrase search for related documents, hyperlinks ordered by date