COVID-19 Diagnosis through Chest X-Ray Images Leveraging VGG16 Architecture

The ongoing COVID-19 pandemic has demanded developing efficient and reliable diagnostic tools to combat the virus's dissemination. In this paper, we have put forward a novel approach based on deep learning for the automated recognition of COVID-19 from chest X-ray images, based on the VGG16 architecture. Utilizing a dataset containing X-ray images of the chest of people who are both COVID-19 positive as well as negative, we trained and evaluated the VGG16 model for its diagnostic performance. Through rigorous experimentation and validation, this proposed model has achieved an remarkable accuracy of 98.2%, demonstrating its worth in effectively differentiating between COVID-19 and non-COVID-19 patients. Furthermore, we conducted extensive comparative analyses with existing approaches, showcasing the superiority of our suggested model in terms of computing efficiency and accuracy. Achieved results highlight the prospective of methodologies based on deep learning, particularly the VGG16 model, as a valuable tool when combating the COVID-19 epidemic, offering rapid and reliable diagnosis to aid in effective patient management and community wellbeing interventions, and the precision, recall, and F1 score of the suggested model yield positive values of 0.98, 0.98, and 0.98.