Transfer Learning Based Convolutional Neural Network (CNN) for Early Diagnosis of Covid19 Disease Using Chest Radiographs

Covid19 is a deadly disease that spreads in the lungs and may result in damaging both the lungs. This infection may be life-threatening if not detected at right time. In this work, chest radiographs were used as the input images. Several pre-trained CNN models such as VGG16 and VGG19 were used for transfer learning. The features were extracted after pre-processing the images. Finally, these images were provided as input to several machine learning classifiers for the classification of images as Covid19 infected or normal chest x-ray images. The classification accuracy of 99.5% was obtained by using the VGG19 model and logistic regression classifier. The results show that the current work will be very useful in the early detection of Covid19 disease to provide in-time treatment to the patients. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.