Automated detection of COVID-19 cases from chest X-ray images using deep neural network and XGBoost

TL;DR

This paper presents a novel method combining DenseNet169 and XGBoost to accurately and efficiently detect COVID-19 from chest X-ray images, outperforming existing approaches.

Contribution

The study introduces a hybrid deep learning and machine learning approach for COVID-19 detection from X-ray images, demonstrating improved accuracy and speed over prior methods.

Findings

Higher detection accuracy than existing methods

Faster classification process

Effective feature extraction with DenseNet169

Abstract

In late 2019 and after COVID-19 pandemic in the world, many researchers and scholars have tried to provide methods for detection of COVID-19 cases. Accordingly, this study focused on identifying COVID-19 cases from chest X-ray images. In this paper, a novel approach to diagnosing coronavirus disease from X-ray images was proposed. In the proposed method, DenseNet169 deep neural network was used to extract the features of X-ray images taken from the patients' chest and the extracted features were then given as input to the Extreme Gradient Boosting (XGBoost) algorithm so that it could perform the classification task. Evaluation of the proposed approach and its comparison with the methods presented in recent years revealed that the proposed method was more accurate and faster than the existing ones and had an acceptable performance in detection of COVID-19 cases from X-ray images.