Deep learning based model for classification of COVID -19 images for healthcare research progress

Saroj Kumar; L Chandra Sekhar Redd; Susheel George Joseph; Vinay Kumar Sharma; Sabireen H

doi:10.1016/j.matpr.2022.04.884

Deep learning based model for classification of COVID -19 images for healthcare research progress

Mater Today Proc. 2022:62:5008-5012. doi: 10.1016/j.matpr.2022.04.884. Epub 2022 May 18.

Authors

Saroj Kumar¹, L Chandra Sekhar Redd², Susheel George Joseph³, Vinay Kumar Sharma⁴, Sabireen H⁵

Affiliations

¹ Sr. Data Scientist, DCG Data-Core Systems India Pvt Ltd, Kolkata, India.
² CMR College of Engineering & Technology, Kandlakoya, Medchal, Hyderabad, India.
³ Department of Computer Application,Kristu Jyoti College of Management and Technology, Changanasery, India.
⁴ CSE, AIT, Chandigarh University, NH-95 Chandigarh-Ludhiana Highway, Mohali, Punjab, India.
⁵ Vellore Institute of Technology, Chennai, India.

Abstract

As imaging technology plays an important role in the diagnosis and evaluation of the new coronavirus pneumonia (COVID-19), COVID-19 related data sets have been published one after another, but there are relatively few data sets and research progress in related literature. To this end, through COVID-19-related journal papers, reports, and related open-source data set websites, organize and analyze the new coronary pneumonia data set and the deep learning models involved, including computed tomography (CT) image data sets and X-ray (CXR) Image dataset. Analyze the characteristics of the medical images presented in these data sets; focus on open-source data sets, as well as classification and segmentation models that perform well on related data sets. Finally, the future development trend of lung imaging technology is discussed.

Keywords: COVID-19 Data Set; Deep Learning; Image Classification; Image Segmentation.

Copyright © 2022 Elsevier Ltd. All rights reserved. Selection and peer-review under responsibility of the scientific committee of the International Conference on Innovative Technology for Sustainable Development.