Efficient Diagnosis of Covid19 by Employing Deep Transfer Learning on Pretrained VGG and ResidualNet Architectures

Covid19 has had a widespread influence on health services and the way of life. A prompt diagnosis is crucial for curbing the development of the disease and lowering the number of fatalities. It is customary and standard routine to employ blood tests to detect presence of pathogen, but because of the time and expense involved, it is often necessary to turn to other rapid and affordable options. We implemented two distinct transference based deep layered architectures in this study i.e., ResidualNet50 along with VGG16, to classify X-rays as COVID19, pneumonia, or normal. ResidualNet50 trained with transference approach outperformed the other deep-learning model i.e., VGG16, in the planned execution. Our proposed transfer deep-learning based model obtained an overall high classification accuracy of 98.5 percent. Result analysis and interpretation via performance curves have been comprehensively discussed in this paper.