The new type of Coronavirus (Covid-19), which was first seen in Wuhan province of the Chinese country in December 2019 and was a highly contagious disease, spread all over the world in just a few months and became a pandemic. Covid-19 has changed the world economic structure, people's religious, political, social life, public health structure, people's daily life structure and left millions of people unemployed. The primary way to combat this epidemic is to diagnose the infected person as soon as possible and remove him from healthy individuals. Currently, Reverse Transcription-Polymerase Chain Reaction (RT-PCR) is used to detect Covid-19 patients worldwide. However, it has been emphasized by the World Health Organization (WHO) that RT-PCR suffers from low sensitivity and low specificity in the detection of early stage cases. Recent research has shown that chest Computed Tomography (CT) scan images play a useful role in identifying Covid-19 cases. In this study, Convolutional Neural Network (CNN) performances were compared with many classification algorithms suitable for the latest technological developments for the prediction model based on the classification results of Covid-19 cases. As a result, it was emphasized that the proposed CNN model performs better than other advanced classification algorithms and achieves 98.1% accuracy.
Özbay, Erdal and A. Özbay, Feyza
"Covid-19 Detection from CT images with Deep Learning and Classification Approaches,"
Dicle University Journal of Engineering: Vol. 12
, Article 3.
Available at: https://duje.dicle.edu.tr/journal/vol12/iss2/3