ABSTRACT
The Corona Virus Disease 2019 (COVID-19) pandemic has affected many people with the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection, and various symptoms are experienced by those affected. A severe SARS-CoV-2 infection could cause respiratory failure and damage to the internal organs, especially the lungs. Thus, diagnosis needs to be done using radiological examination. The difficulty to distinguish COVID-19 markers from some other diseases, such as pneumonia, creates a challenge. Also, not every health center has a radiologist to make the diagnosis, which is the situation particularly in many least developed and developing countries. This research proposes the use of deep learning technique for the automatic detection of COVID-19 with chest X-ray (CXR) images, which is the most commonly available and affordable medical images. The focus is to accurately distinguish between COVID-19, Pneumonia and healthy CXR. The Visual Geometry Group version 16 (VGG-16) architecture of the convolutional neural network (CNN) algorithm is exploited, and then some performance metrics are produced for evaluation and analysis in searching for better approaches for the final model. The Graphical User Interface (GUI) design and the embedded system implementation are also developed, allowing to build an affordable but reliable portable detection system to assist radiologist to perform fast and accurate diagnosis of COVID-19 and pneumonia through patients CXR.
