FCOD: Fast COVID-19 Detector based on deep learning techniques

Published in Informatics in medicine unlocked, 2021

The sudden COVID-19 pandemic has caused serious global concern due to infection and mortality rates. It is a hazardous disease that has become one of the biggest crises of the modern era. Due to the limited availability of test kits and the need for rapid screening and diagnosis, it is essential to develop a self-operating detection model to identify COVID-19 infections and prevent their spread among people. In this paper, we propose a novel technique called Fast COVID-19 Detector (FCOD) for the rapid detection of COVID-19 using X-ray images. FCOD is a deep learning model based on the Inception architecture that uses 17 depthwise separable convolution layers to detect COVID-19. Depthwise separable convolution layers reduce computational costs and processing time while decreasing the number of parameters compared to standard convolution layers. To evaluate FCOD, we used the COVID-ChestXRay dataset, which contains 940 publicly available chest X-ray images. Our results show that FCOD can achieve an accuracy, F1-score, and AUC of 96%, 96%, and 95%, respectively, in classifying COVID-19 in 0.014 seconds per case. The proposed model can be employed as a supportive decision-making system to assist radiologists in clinics and hospitals in screening patients immediately.