Metaheuristic-based Deep COVID-19 Screening Model from Chest X-Ray Images

Manjit Kaur; Vijay Kumar; Vaishali Yadav; Dilbag Singh; Naresh Kumar; Nripendra Narayan Das

doi:10.1155/2021/8829829

Metaheuristic-based Deep COVID-19 Screening Model from Chest X-Ray Images

J Healthc Eng. 2021 Mar 1:2021:8829829. doi: 10.1155/2021/8829829. eCollection 2021.

Authors

Manjit Kaur¹, Vijay Kumar², Vaishali Yadav³, Dilbag Singh¹, Naresh Kumar⁴, Nripendra Narayan Das⁵

Affiliations

¹ Computer Science Engineering, School of Engineering and Applied Sciences, Bennett University, Greater Noida, 201310, India.
² Department of Computer Science and Engineering, National Institute of Technology Hamirpur, Hamirpur, Himachal Pradesh, 177005, India.
³ Department of Computer and Communication Engineering, School of Computing and Information Technology, Manipal University Jaipur, Jaipur, Rajasthan, 303007, India.
⁴ Department of Computer Science and Engineering, Maharaja Surajmal Institute of Technology, C-4 Block, Janakpuri, New Delhi 110058, India.
⁵ Department of Information Technology, School of Computing and Information Technology, Manipal University Jaipur, Jaipur, Rajasthan, 303007, India.

Abstract

COVID-19 has affected the whole world drastically. A huge number of people have lost their lives due to this pandemic. Early detection of COVID-19 infection is helpful for treatment and quarantine. Therefore, many researchers have designed a deep learning model for the early diagnosis of COVID-19-infected patients. However, deep learning models suffer from overfitting and hyperparameter-tuning issues. To overcome these issues, in this paper, a metaheuristic-based deep COVID-19 screening model is proposed for X-ray images. The modified AlexNet architecture is used for feature extraction and classification of the input images. Strength Pareto evolutionary algorithm-II (SPEA-II) is used to tune the hyperparameters of modified AlexNet. The proposed model is tested on a four-class (i.e., COVID-19, tuberculosis, pneumonia, or healthy) dataset. Finally, the comparisons are drawn among the existing and the proposed models.

MeSH terms

Algorithms
COVID-19 / diagnostic imaging*
Deep Learning*
Humans
Image Interpretation, Computer-Assisted / methods*
Neural Networks, Computer
Radiography, Thoracic*
Sensitivity and Specificity