Related Experiment Video
Updated: Sep 1, 2025
04:17
DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
Published on: May 10, 2024
861
An Effective Deep Learning Model for Health Monitoring and Detection of COVID-19 Infected Patients: An End-to-End
Vidyadevi G Biradar1, Mejdal A Alqahtani2, H C Nagaraj3
1Department of Information Science and Engineering, Nitte Meenakshi Institute of Technology, Bangalore, India.
Computational Intelligence and Neuroscience
|August 15, 2022
Summary
This study introduces a convolutional neural network for rapid COVID-19 detection using chest X-rays. The developed tool offers a cost-effective, automated solution for timely diagnosis and disease control.
Area of Science:
- Artificial Intelligence
- Medical Imaging
- Infectious Disease Diagnostics
Background:
- COVID-19 poses a significant global health threat, necessitating rapid and accurate diagnostic methods.
- Traditional diagnostic approaches for COVID-19 are often time-consuming, costly, and labor-intensive.
- There is a critical need for efficient, automated tools to facilitate widespread and timely testing.
Purpose of the Study:
- To develop and evaluate a convolutional neural network (CNN) model for analyzing chest X-ray images to detect COVID-19 infections.
- To identify optimal pre-trained deep learning models for integration into portable diagnostic tools.
- To create a user-friendly, end-to-end solution including mobile and web applications for patient and healthcare provider use.
Main Methods:
- Utilized a convolutional neural network (CNN) architecture for the analysis of chest X-ray images.
- Investigated various pre-trained deep learning models to determine the most suitable for COVID-19 detection.
- Developed integrated mobile and web applications to support the diagnostic tool, enabling appointment booking and result delivery.
Main Results:
- The proposed CNN model demonstrates potential for effective COVID-19 detection from frontal chest X-ray images.
- The study identified suitable deep learning models for integration into mobile diagnostic applications.
- An end-to-end system with a user-friendly interface was successfully created, facilitating accessibility for medical practitioners.
Conclusions:
- The developed AI-powered tool shows promise as a cost-effective and efficient solution for COVID-19 screening.
- The integration of the model into portable diagnostic instruments and applications can enhance disease surveillance and management.
- The system offers a practical approach for real-world application in clinical settings, aiding timely diagnosis.
