Deep learning driven framework for COVID-19 detection – A Mobile/Web application

Abstract

Due to the rapid spread of COVID-19, this disease has become a global threat to public health. COVID-19 detection via radiographic images such as CXR and HRCT is one of the most effective techniques. Using deep Learning models, the current study investigates COVID-19 disease on radiographic images. This project proposes a deep learning model for HRCT and CXR images to predict a patient's condition. The proposed model classifies images by incorporating VGG16 deep learning models. In addition, symptom analysis is performed to forecast COVID-19. For symptom analysis, the xgboost algorithm is used. Lastly, a mobile/web application for detecting COVID-19 using deep learning models on radiographic images is developed. This work may serve as a resource for other researchers seeking to advance the development of deep learning applications for medical imaging.