DeepCOVID: a deep learning approach for accurate COVID-19 detection in point-of-care lung ultrasound

Abstract

Sickness still continued to spread through several countries when it first appeared in China. The number of COVID-19 cases is rising daily worldwide, posing a severe threat to the government and the populace. As a result of the virus’s rapid spread, doctors are having trouble recognizing positive cases. It is obvious that computer-based diagnosis must be developed to get results at a reasonable cost. The classic convolutional neural network (CNN) is used for this, utilizing the CT dataset, and the upgraded CNN model is used with the lung ultrasound (LUS) dataset. The CT and LUS COVID imaging datasets are compared in the model. The accuracy of both deep learning models is higher. We customized ResNet50, a pre-trained deep learning architecture, for a web application paradigm. First, we suggest a method for normalizing data that addresses its variability because it is collected in hospitals using various CT scanners and ultrasound machines. Second, we identify COVID-19 patients using U-Net segmentation and classification. The CNN architecture is added for deep learning purposes, and Res-Net 50 offers incredible accuracy.