COVID-19 detection from chest X-Ray images using Deep Learning and Convolutional Neural Networks

What is it about?

In this research work the effectiveness of several state-of-the-art pre-trained convolutional neural networks was evaluated regarding the automatic detection of COVID-19 disease from chest X-Ray images. A collection of 336 X-Ray scans in total from patients with COVID-19 disease, bacterial pneumonia and normal incidents is processed and utilized to train and test the CNNs. Due to the limited available data related to COVID-19, the transfer learning strategy is employed.

Featured Image

Photo by CDC on Unsplash

Photo by CDC on Unsplash

Why is it important?

The COVID-19 pandemic in 2020 has highlighted the need to pull all available resources towards the mitigation of the devastating effects of such "Black Swan" events. Towards that end, we investigated the option to employ technology in order to assist the diagnosis of patients infected by the virus. As such, several state-of-the-art pre-trained convolutional neural networks were evaluated as of their ability to detect infected patients from chest X-Ray images. The main difference between our work and the previous studies is that this study incorporates a large number of CNN architectures in an attempt to not only distinguish X-Rays between COVID-19 patients and people without the disease, but to also discriminate pneumonia patients from patients with the corona virus, acting as a classifier of respiratory diseases. The experimental results demonstrate that the classification performance can reach an accuracy of 95% for the best two models.