An efficient technique for CT scan images classification of COVID-19

Nowadays, Coronavirus (COVID-19) considered one of the most critical pandemics in earth. This is due its ability to spread rapidly between humans as well animals. COVID-19 expected outbreak around world, 70 % earth population might infected with incoming years. Therefore, an accurate and efficient diagnostic tool highly required, which main objective our study. Manual classification was mainly used detect different diseases, but it took too much time addition probability human errors. Automatic image reduces doctors time, could save human’s life. We propose automatic architecture based on deep neural network called Worried Deep Neural Network (WDNN) model transfer learning. Comparative analysis reveals that proposed WDNN outperforms by using three pre-training models: InceptionV3, ResNet50, VGG19 terms various performance metrics. Due shortage data set, augmentation increase number images positive class, then normalization make all have same size. Experimentation done dataset collected from cases total 2623 where (1573 training, 524 validation, test). Our achieved 99,046, 98,684, 99,119, 98,90 accuracy, precision, recall, F-score, respectively. The results are compared both traditional machine learning methods those Convolutional Networks (CNNs). demonstrate use alternative current tool.