COVID-CXNet: Detecting COVID-19 in Frontal Chest X-ray Images using Deep Learning

TL;DR

COVID-CXNet leverages deep learning and transfer learning on a large dataset of chest X-ray images to accurately detect COVID-19 pneumonia, emphasizing relevant features for improved diagnosis.

Contribution

The paper introduces COVID-CXNet, a deep learning model based on CheXNet, utilizing a large, diverse dataset and transfer learning to enhance COVID-19 detection accuracy from chest X-rays.

Findings

COVID-CXNet achieves high detection accuracy.

The model localizes relevant imaging features.

Pretrained networks focus on irrelevant features without proper training.

Abstract

One of the primary clinical observations for screening the infectious by the novel coronavirus is capturing a chest x-ray image. In most of the patients, a chest x-ray contains abnormalities, such as consolidation, which are the results of COVID-19 viral pneumonia. In this study, research is conducted on efficiently detecting imaging features of this type of pneumonia using deep convolutional neural networks in a large dataset. It is demonstrated that simple models, alongside the majority of pretrained networks in the literature, focus on irrelevant features for decision-making. In this paper, numerous chest x-ray images from various sources are collected, and the largest publicly accessible dataset is prepared. Finally, using the transfer learning paradigm, the well-known CheXNet model is utilized for developing COVID-CXNet. This powerful model is capable of detecting the novel coronavirus pneumonia based on relevant and meaningful features with precise localization. COVID-CXNet is a step towards a fully automated and robust COVID-19 detection system.