CLASSIFICATION OF COVID, PNEUMONIA, OR STANDARD X-RAY IMAGES USING A NEURAL NETWORK

Abstract

The current global Covid-19 pandemic is linked to SARS-CoV-2, an acute respiratory disease caused by a new coronavirus that is highly contagious and whose evolution is unidentified. More than 1 million cases of Covid-19 infection have been confirmed worldwide using the existing case definition, based on the diagnosis of Pneumonia, and the associated mortality rate has fluctuated around 2%. Current laboratory tests may not be widely available to a growing infected population, but new screening strategies are required. Chest CT as a screening tool has yet to be determined. Recent studies have demonstrated a central role of CT in the early detection and management of Covid-19 pulmonary manifestations. It has shown high sensitivity but limited specificity. We present a Neural Network in TensorFlow and Keras based on Covid-19 and Pneumonia classification. The proposed system is based on CNN using images to classify Covid-19 or Pneumonia in this system using the CNN model. It is predicted that the success of the obtained results will increase if the CNN method is supported by adding different feature extraction methods and images to classify successfully by covid-19 or Pneumonia. Keywords: Deep Learning, TensorFlow, Keras, CNN