Automatic method for classifying COVID-19 patients based on chest X-ray images, using deep features and PSO-optimized XGBoost

作者：

Highlights：

• A method to classify patients in COVID-19 or non-COVID-19 based on Chest X-Rays.

• We introduce a deep features extraction with XGBoost optimized by PSO.

• The method was developed and tested on two public databases.

• We evaluate our work in 1547 CXR images.

• The method achieved an accuracy of 98.71%, precision of 98.89%, recall of 99.63%, and F1-score of 99.25%.

摘要

•A method to classify patients in COVID-19 or non-COVID-19 based on Chest X-Rays.•We introduce a deep features extraction with XGBoost optimized by PSO.•The method was developed and tested on two public databases.•We evaluate our work in 1547 CXR images.•The method achieved an accuracy of 98.71%, precision of 98.89%, recall of 99.63%, and F1-score of 99.25%.

论文关键词：Chest X-Rays,COVID-19,Deep features,Medical images,Particle swarm optimization,Extreme gradient boosting

论文评审过程：Received 30 September 2020, Revised 18 February 2021, Accepted 14 June 2021, Available online 22 June 2021, Version of Record 22 June 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115452