A CNN based coronavirus disease prediction system for chest X-rays
- 27 February 2022
- journal article
- research article
- Published by Springer Nature in Journal of Ambient Intelligence and Humanized Computing
- Vol. 14 (10) , 13179-13193
Abstract
Coronavirus disease (COVID-19) proliferated globally in early 2020, causing existential dread in the whole world. Radiography is crucial in the clinical staging and diagnosis of COVID-19 and offers high potential to improve healthcare plans for tackling the pandemic. However high variations in infection characteristics and low contrast between normal and infected regions pose great challenges in preparing radiological reports. To address these challenges, this study presents CODISC-CNN (CNN based Coronavirus DIsease Prediction System for Chest X-rays) that can automatically extract the features from chest X-ray images for the disease prediction. However, to get the infected region of X-ray, edges of the images are detected by applying image preprocessing. Furthermore, to attenuate the shortage of labeled datasets data augmentation has been adapted. Extensive experiments have been performed to classify X-ray images into two classes (Normal and COVID), three classes (Normal, COVID, and Virus Bacteria), and four classes (Normal, COVID, and Virus Bacteria, and Virus Pneumonia) with the accuracy of 97%, 89%, and 84% respectively. The proposed CNN-based model outperforms many cutting-edge classification models and boosts state-of-the-art performance.Keywords
This publication has 37 references indexed in Scilit:
- Clinical features of patients infected with 2019 novel coronavirus in Wuhan, ChinaThe Lancet, 2020
- Re-epithelialization and immune cell behaviour in an ex vivo human skin modelScientific Reports, 2020
- Introduction to convolutional neural network using Keras; an understanding from a statisticianCommunications for Statistical Applications and Methods, 2019
- Deep Generalized Max Pooling2019
- Focus Is All You Need: Loss Functions for Event-Based Vision2019
- ImageNet classification with deep convolutional neural networksCommunications of the ACM, 2017
- Learning Multi-domain Convolutional Neural Networks for Visual Tracking2016
- Absolute Humidity, Temperature, and Influenza Mortality: 30 Years of County-Level Evidence from the United StatesAmerican Journal of Epidemiology, 2012
- Probabilistic model of influenza virus transmissibility at various temperature and humidity conditionsComputational Biology and Chemistry, 2009
- Influenza Virus Transmission Is Dependent on Relative Humidity and TemperaturePLOS Pathogens, 2007