Deep COVID-19 Recognition using Chest X-ray Images: A Comparative Analysis

TL;DR

This paper evaluates various deep learning models for COVID-19 detection using chest X-ray images, finding that EfficientNetB7 achieves the best performance among tested networks.

Contribution

It provides a comparative analysis of state-of-the-art deep networks for COVID-19 recognition from chest X-ray images, highlighting EfficientNetB7's superior performance.

Findings

Deep networks effectively recognize COVID-19 from X-ray images.

EfficientNetB7 outperforms other models in accuracy.

Deep learning models reduce pre-processing complexity.

Abstract

The novel coronavirus variant, which is also widely known as COVID-19, is currently a common threat to all humans across the world. Effective recognition of COVID-19 using advanced machine learning methods is a timely need. Although many sophisticated approaches have been proposed in the recent past, they still struggle to achieve expected performances in recognizing COVID-19 using chest X-ray images. In addition, the majority of them are involved with the complex pre-processing task, which is often challenging and time-consuming. Meanwhile, deep networks are end-to-end and have shown promising results in image-based recognition tasks during the last decade. Hence, in this work, some widely used state-of-the-art deep networks are evaluated for COVID-19 recognition with chest X-ray images. All the deep networks are evaluated on a publicly available chest X-ray image dataset. The evaluation results show that the deep networks can effectively recognize COVID-19 from chest X-ray images. Further, the comparison results reveal that the EfficientNetB7 network outperformed other existing state-of-the-art techniques.