Classification of COVID-19 and lung opacity using vision transformer on chest x-ray images
There are several recent works which had proposed an automatic computer-aided diagnosis (CAD) deep learning (DL) model to diagnose coronavirus disease 2019 (COVID-19) using chest x-ray images (CXR) to propose a high-accuracy CAD method to detect COVID-19 automatically. In this study, seven different...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English |
| Published: |
2023
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/107885/1/UsmanUllahSheikh2023_ClassificationofCOVID19andLungOpacity.pdf http://eprints.utm.my/107885/ http://dx.doi.org/10.1088/1742-6596/2622/1/012016 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | There are several recent works which had proposed an automatic computer-aided diagnosis (CAD) deep learning (DL) model to diagnose coronavirus disease 2019 (COVID-19) using chest x-ray images (CXR) to propose a high-accuracy CAD method to detect COVID-19 automatically. In this study, seven different models including Convolutional Neural Network (CNN) models such as VGG-16 and vision transformer (ViT) models, are proposed. The different proposed models are trained with a three-class balanced dataset consisting of 3,000 CXR images consisting of 1,000 CXR images for each class of COVID-19, Normal, and Lung-Opacity. A publicly available dataset to train and test the models is used from Kaggle-COVID-19-Radiography-Dataset. From the experiments, the accuracy of the VGG16 model is 93.44% and ViT's is 92.33%. Besides, the binary classification between two classes of COVID-19 and Normal CXR with a limited number of just 100 images for each class, using a transfer learning technique, with a validation accuracy of 97.5% is proposed. |
|---|