COVID-19 is a pandemic that originated in Wuhan, China in 2019 and is caused by SARS-CoV-2 viruses. The pandemic quickly spread all over the world due to the high contagiousness of the virus. Symptoms exhibited by SARS-CoV-2 viruses can be similar to other diseases and diseases of those exposed to the virus can be confused with viral pneumonia. Therefore, computer-aided diagnosis (CAD) systems are used to assist doctors and researchers in the diagnosis of the disease. In this study, the COVID-19 data set, which includes 3 classes, was classified using the transfer learning method. 80% of the data set is separated as training and 20% as test data. Classifiers constructed using pre-trained models were trained and the accuracy rates for the test data were obtained as %98.6, %98.7, %99.3, %97.8, %98.7 and %98.0 for InceptionV3, Xception, InceptionResNetV2, VGG19, ResNet152V2, DenseNet201 models, respectively. These results show that the proposed classifiers based on pre-trained models can assist doctors in the diagnosis of the COVID-19 outbreak.
Benzer Makaleler | Yazar | # |
---|
Makale | Yazar | # |
---|