Open AccessCOVD-19 Detection Platform from X-ray Images using Deep Learning
Author(s) -
Mohammed Elbes,
Tarek Kanan,
Mohammad Alia,
Mohammad Ziad
Publication year - 2022
Publication title -
international journal of advances in soft computing and its applications
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.15
H-Index - 18
eISSN - 2710-1274
pISSN - 2074-8523
DOI - 10.15849/ijasca.220328.13
Subject(s) - convolutional neural network , covid-19 , deep learning , artificial intelligence , computer science , radiological weapon , selection (genetic algorithm) , test (biology) , work (physics) , machine learning , pattern recognition (psychology) , medicine , radiology , disease , pathology , engineering , mechanical engineering , paleontology , biology , outbreak , infectious disease (medical specialty)
Since the early days of 2020, COVID-19 has tragic effects on the lives of human beings all over the world. To combat this disease, it is important to survey the infected patients in an inexpensive and fast way. One of the most common ways of achieving this is by performing radiological testing using chest X-Rays and patient coughing sounds. In this work, we propose a Convolutional Neural Network-based solution which is able to identify the positive COVID-19 patients using chest XRay images. Multiple CNN models have been adopted in our work. Each of these models provides a decision whether the patient is affected with COVID-19 or not. Then, a weighted average selection technique is used to provide the final decision. To test the efficiency of our model we have used publicly available chest X-ray images of COVID positive and negative cases. Our approach provided a classification performance of 88.5%. Keywords: COVID-19, CT-Images, Deep Learning, CNN Algorithm.