COVID-19 DETECTION FROM X-RAY IMAGES USING CONVOLUTIONAL NEURAL NETWORK

Abstract

Without any cause, pneumonia was detected in Wuhan, China. It was first reported to the WHO in
December 2019. Corona virus disease 2019 (COVID-19) is an infectious disease caused by severe acute
respiratory syndrome corona virus 2 (SARS- CoV-2). Detection of this disease (COVID-19) is an
emergent necessity for society as its spread is rapid. Till date no specific symptom is defined. Also
research is in progress for development of medicine and vaccine. However, clinical diagnosis provides
the result of infection for which less amount of data are available. As detection is an important criterion,
in this work we have designed a convolutional neural network (CNN) model to detect from infected X-ray
image. The dataset of X-ray images are collected from online sources available for research purposes.
The proposed model is trained and tested with chest X-ray images and to evaluate the model we have
used categorical cross entropy loss. The proposed model is trained with Adam optimizer. The detection
result found excellent and explained in result section.