Open AccessDEEP LEARNING (CNN) MODEL FOR COVID-19 DETECTION FROM CHEST XRAY IMAGES
Author(s) -
Ahmed A. B. Mohamed,
Ahmed L. Abdelhady
Publication year - 2021
Publication title -
international journal of engineering applied science and technology
Language(s) - English
Resource type - Journals
ISSN - 2455-2143
DOI - 10.33564/ijeast.2021.v06i04.010
Subject(s) - convolutional neural network , covid-19 , deep learning , artificial intelligence , computer science , stage (stratigraphy) , outbreak , disease , medicine , radiology , pattern recognition (psychology) , pathology , infectious disease (medical specialty) , biology , paleontology
The Coronavirus disease outbreak resultin many people to have severe respira- toryproblems and it was recognized as a global healththreat. Since the virus is targeting the lungs in thehuman body initially, chest x-ray imaging featureswere considered to be useful for the detection of theinfection in the early stage. In this study, the chestx-ray data of 130 infected patients from an opendata source that referenced Cohen J. Morrison P.Dao L., 2020 was used to build a CNN(Convolutional Neural-Network) model for theearly detection of the disease. The model wastrained with both infected and not-infectedpeoples’ chest x-ray images with 100 epochs whichled to 0.98 accuracy finally. In order to use thismodel as a professional diagnosis element, it ishighly recommended it be improved with moreimages and the model can be restructured to get abetter accuracy.