A new approach for classifying coronavirus COVID-19 based on its manifestation on chest X-rays using texture features and neural networks

Sergio Varela-Santos; Patricia Melin

doi:10.1016/j.ins.2020.09.041

A new approach for classifying coronavirus COVID-19 based on its manifestation on chest X-rays using texture features and neural networks

Inf Sci (N Y). 2021 Feb 4:545:403-414. doi: 10.1016/j.ins.2020.09.041. Epub 2020 Sep 24.

Authors

Sergio Varela-Santos¹, Patricia Melin¹

Affiliation

¹ Division of Graduate Studies, Tijuana Institute of Technology, Tijuana, 22414 Baja CA, Mexico.

Abstract

Since the recent challenge that humanity is facing against COVID-19, several initiatives have been put forward with the goal of creating measures to help control the spread of the pandemic. In this paper we present a series of experiments using supervised learning models in order to perform an accurate classification on datasets consisting of medical images from COVID-19 patients and medical images of several other related diseases affecting the lungs. This work represents an initial experimentation using image texture feature descriptors, feed-forward and convolutional neural networks on newly created databases with COVID-19 images. The goal was setting a baseline for the future development of a system capable of automatically detecting the COVID-19 disease based on its manifestation on chest X-rays and computerized tomography images of the lungs.

Keywords: COVID-19; GLCM; Image Classification; Neural Networks; Pneumonia; X-ray.