Automated Detection of COVID-19 Pneumonia and Non COVID-19 Pneumonia from Chest X-ray Images Using Convolutional Neural Network (CNN) | IEEE Conference Publication | IEEE Xplore

Automated Detection of COVID-19 Pneumonia and Non COVID-19 Pneumonia from Chest X-ray Images Using Convolutional Neural Network (CNN)


Abstract:

SARS-CoV-2 has now spread to nearly every part of the world, with the WHO declaring a pandemic because of its rapid spread. One of the diagnostic procedures used to detec...Show More

Abstract:

SARS-CoV-2 has now spread to nearly every part of the world, with the WHO declaring a pandemic because of its rapid spread. One of the diagnostic procedures used to detect the extent of the COVID-19 infection is Chest X-rays. Chest Xrays are commonly used to diagnose lung disorders in the beginning. To improve the accuracy of the computer- aided diagnosis system, a research study assessed how well it can correctly distinguish between non-COVID-19 pneumonia on chest X-ray (CXR) images and COVID-19 pneumonia with the alliance of Artificial Intelligence. COVID-19 pneumonia patients (those that tested positive for COVID-19 antibodies) and non- COVID-19 pneumonia patients (those who did not test positive for COVID-19 antibodies) were included in the analysis. The research was conducted using a standard dataset containing 1563 lung CT scan images of COVID-19 pneumonia and non-COVID-19 pneumonia (virus) patients' samples. The proposed system has two Convolutional Neural Network (CNN) models. The first CNN model using max pooling operation achieved the accuracy, precision, recall, and F1-Score of 98.22%, 98.81 %, 99.33%, and 99.07% respectively and similarly, the second CNN model using average pooling operation performed at 97.82%, 98.60%, 99.13%, and 98.86% respectively
Date of Conference: 23-25 September 2021
Date Added to IEEE Xplore: 09 November 2021
ISBN Information:
Conference Location: Salatiga, Indonesia

References

References is not available for this document.