Comparing Different Deep Learning Models with a Novel Model for COVID-19 and Pneumonia Classification Using Chest X-Ray Images.

The global impact of the COVID-19 pandemic has created a significant health crisis affecting millions worldwide. Clinical symptom assessment and chest X-ray tomography are regularly consumed for diagnosing and monitoring COVID-19. To contribute to this effort, our research conducted a comparative analysis of various deep-learning (DL) models for categorizing chest X-ray images of pneumonia and COVID-19, introducing a novel model that outperforms existing ones. The pandemic has intensified the need for prompt diagnosis and treatment. Crucially, chest X-ray imaging has a fundamental role in identifying and tracking the progression of COVID-19. Evaluating our approach on a publicly available chest X-ray dataset, we achieved exceptional accuracy, sensitivity, and specificity rates of 95.7%, 94.3%, and 96.9%, respectively. These results underscore the skill of DL-based approaches in automated COVID-19 discovery from images of chest X-Ray tomography, facilitating swift and accurate diagnosis. Our research demonstrates the promising capacity of DL methods for rapid and precise identification of COVID-19 disease from X-ray images, offering valuable support for timely diagnosis of the condition.