Abstract:

Throughout history, humanity has continually faced numerous unforeseen health crises, thereby emphasizing the utmost significance of harnessing cutting-edge technology and scientific approaches to proactively anticipate and tackle potential outbreaks. In the context of the COVID-19 pandemic, the utilization of CT scans has proven to be an indispensable asset in accurately detecting and diagnosing individuals afflicted with COVID-19. By virtue of their advanced imaging capabilities and ability to capture detailed internal images, CT scans have emerged as a pivotal diagnostic tool in the fight against this infectious disease. The objective of this study is to improve the precision and effectiveness of COVID-19 diagnosis by employing a convolutional neural network (CNN) model architecture specifically tailored for the analysis of CT images. We conducted a comprehensive analysis of the current body of literature to investigate the clinical features, imaging  manifestations, and image-based diagnostic methods of COVID-19. This study examines the application of deep learning models in the diagnosis of COVID-19, specifically emphasizing the utilization of Convolutional Neural Networks (CNNs) as a robust method for analyzing medical images. In addition, we demonstrate experimental enhancements to the CNN model, achieving a diagnosis accuracy of up to 92.80% when evaluated on test data.