A bagging dynamic deep learning network for diagnosing COVID-19

Bozhao Chen,Jiansheng Sun,Zhijun Zhang,Yamei Luo

doi:10.1038/s41598-021-95537-y

Abstract

COVID-19 is a serious ongoing worldwide pandemic. Using X-ray chest radiography images for automatically diagnosing COVID-19 is an effective and convenient means of providing diagnostic assistance to clinicians in practice. This paper proposes a bagging dynamic deep learning network (B-DDLN) for diagnosing COVID-19 by intelligently recognizing its symptoms in X-ray chest radiography images. After a series of preprocessing steps for images, we pre-train convolution blocks as a feature extractor. For the extracted features, a bagging dynamic learning network classifier is trained based on neural dynamic learning algorithm and bagging algorithm. B-DDLN connects the feature extractor and bagging classifier in series. Experimental results verify that the proposed B-DDLN achieves 98.8889% testing accuracy, which shows the best diagnosis performance among the existing state-of-the-art methods on the open image set. It also provides evidence for further detection and treatment.

Highlights

COVID-19 is a serious ongoing worldwide pandemic
For a faster and more accurate COVID-19 diagnosis, this paper proposes a bagging dynamic deep learning network (B-DDLN) that consists of two modules: a feature extractor and a bagging classifier
The application of the proposed B-DDLN to diagnose the presence of COVID-19 by analyzing X-ray chest radiography images is described. This description consists of six parts: description and preprocessing of image set, feature extraction, analysis and random under-sampling of samples, experimental results of the proposed B-DDLN, and comparisons between B-DDLN and other diagnosis models

Summary

Introduction

COVID-19 is a serious ongoing worldwide pandemic. Using X-ray chest radiography images for automatically diagnosing COVID-19 is an effective and convenient means of providing diagnostic assistance to clinicians in practice. Given the limitations of nucleic acid amplification testing, the recognition of COVID-19 indications in X-ray chest radiography images can be performed to identify COVID-19 patients, which makes the diagnosis of the disease and its severity more intuitive[8,9]. This is a vital verification method with simple operation. To further improve the diagnostic effect, Majeed et al designed a convolutional neural network (CNN) model for COVID-19 detection from X-ray chest radiography images that obtained 0.9315 sensitivity and 0.9786 s pecificity[16]. The generalization performance of fully connected layer at the end of ResNet-based models may not be strong enough to discriminate and classify deep convolutional features[28]

Results

Discussion

Conclusion