Parameter based Performance Evaluation of Deep Learning Models for Classification of CoViD and Pneumonia CT Images

Abstract

Computer Tomography (CT) scan is one of the widely used techniques to identify Corona Virus Disease-2019. The presence of infection is identified using ground glass opacity in these images. Sometimes, there are very few changes that cannot be identified with the naked eye. Deep learning algorithms can be used to classify such images. Many deep learning algorithms have performed exceptionally well in classifying images. In this paper, we evaluated VGG16 and Xception models and found that the Xception model has a large number of non-trainable parameters. VGG16 model uses a normal convolution and Xception uses a depth wise separable convolution with Batch Normalization. Our results show that VGG16 performs better in classifying CoViD CT Images than the Xception model. We conclude that due to the Batch Normalization Xception model has non-trainable parameters and shows low performance when lesser images are used to train the model. However, VGG16 was found to perform very well even on images with subtle opacity.