Abstract: The expanding number of people suffering from covid-19 is putting a strain on healthcare systems all around the world. Traditional approaches cannot be used to treat every patient with a respiratory infection because to the limited number of diagnostic tools available. Deep Learning has become increasingly popular in recent years, and it currently serves a critical role in picture classification, notably in medical imaging. Convolutional Neural Networks have been used to successfully diagnose a variety of diseases, including coronary artery disease, malaria, Alzheimer's disease, and other dental issues (CNNs). The test also has a long turnaround time and a low sensitivity. According to the study, infected patients displayed certain radiographic visual characteristics such as fever, dry cough, fatigue, and dyspnoea. X-ray machines are available at all healthcare facilities, and samples do not need to be transferred. This research suggests using a chest x-ray to classify the patient's selection for further testing and therapy. The use of chest X-ray images to diagnose the coronavirus responsible for coronavirus sickness 2019 (COVID-19) is life-saving for both patients and doctors. This is especially significant in countries where laboratory testing kits are unavailable. This study shows how the size of the dataset and the number of convolutional layers affect classification outcomes.
Keywords: Covid-19, Convolutional Neural Networks, chest X-ray images, life-saving, Dataset.
Copyright Form