Identification of COVID-19 samples from chest X-Ray images using deep learning: A comparison of transfer learning approaches

The novel coronavirus disease 2019 (COVID-19) constitutes a public health emergency globally. The number of infected people and deaths are proliferating every day, which is putting tremendous pressure on our social and healthcare system. Rapid detection of COVID-19 cases is a significant step to fig...

Full description

Saved in:
Bibliographic Details
Published in:Journal of X-ray science and technology Vol. 28; no. 5; p. 821
Main Authors: Rahaman, Md Mamunur, Li, Chen, Yao, Yudong, Kulwa, Frank, Rahman, Mohammad Asadur, Wang, Qian, Qi, Shouliang, Kong, Fanjie, Zhu, Xuemin, Zhao, Xin
Format: Journal Article
Language:English
Published: Netherlands 01.01.2020
Subjects:
Algorithms
Betacoronavirus
Coronavirus Infections - diagnostic imaging
COVID-19
Databases, Factual
Deep Learning
Diagnosis, Differential
Humans
Neural Networks, Computer
Pandemics
Pneumonia - diagnostic imaging
Pneumonia, Viral - diagnostic imaging
Radiography, Thoracic
Reproducibility of Results
SARS-CoV-2
Tomography, X-Ray Computed - methods
COVID-19
image identification
transfer learning
Chest X-Ray Image
ISSN:1095-9114, 1095-9114
Online Access:Get more information
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The novel coronavirus disease 2019 (COVID-19) constitutes a public health emergency globally. The number of infected people and deaths are proliferating every day, which is putting tremendous pressure on our social and healthcare system. Rapid detection of COVID-19 cases is a significant step to fight against this virus as well as release pressure off the healthcare system. One of the critical factors behind the rapid spread of COVID-19 pandemic is a lengthy clinical testing time. The imaging tool, such as Chest X-ray (CXR), can speed up the identification process. Therefore, our objective is to develop an automated CAD system for the detection of COVID-19 samples from healthy and pneumonia cases using CXR images. Due to the scarcity of the COVID-19 benchmark dataset, we have employed deep transfer learning techniques, where we examined 15 different pre-trained CNN models to find the most suitable one for this task. A total of 860 images (260 COVID-19 cases, 300 healthy and 300 pneumonia cases) have been employed to investigate the performance of the proposed algorithm, where 70% images of each class are accepted for training, 15% is used for validation, and rest is for testing. It is observed that the VGG19 obtains the highest classification accuracy of 89.3% with an average precision, recall, and F1 score of 0.90, 0.89, 0.90, respectively. This study demonstrates the effectiveness of deep transfer learning techniques for the identification of COVID-19 cases using CXR images.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:1095-9114
1095-9114
DOI:10.3233/XST-200715