Related Experiment Video
Updated: Oct 31, 2025
04:17
DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
Published on: May 10, 2024
1.1K
Artificial Neural Network-Based Deep Learning Model for COVID-19 Patient Detection Using X-Ray Chest Images
Mohammad Shorfuzzaman1, Mehedi Masud1, Hesham Alhumyani2
1Department of Computer Science, College of Computers and Information Technology, Taif University, Taif 21974, Saudi Arabia.
Journal of Healthcare Engineering
|July 1, 2021
Summary
A novel deep learning fusion framework using convolutional neural networks (CNNs) accurately detects COVID-19 from chest X-rays. This AI approach achieves 95.49% accuracy, aiding in rapid diagnosis during the pandemic.
Area of Science:
- Artificial Intelligence
- Medical Imaging
- Computational Biology
Background:
- The COVID-19 pandemic necessitates rapid and accurate diagnostic tools.
- Chest X-ray (CXR) imaging reveals radiological patterns indicative of COVID-19 infection.
- Manual detection of these patterns is challenging and time-consuming for radiologists.
Purpose of the Study:
- To develop and evaluate a novel deep learning fusion framework for COVID-19 detection using CXR images.
- To improve the accuracy and efficiency of COVID-19 screening and diagnosis.
- To visualize and understand the feature representations learned by the model.
Main Methods:
- A convolutional neural network (CNN) based deep learning fusion framework was proposed.
- Transfer learning was employed, combining parameters from different models.
- Gradient-weighted class activation mapping (Grad-CAM) was used for visualization.
Main Results:
- The best performing fusion model achieved a classification accuracy of 95.49%.
- The model demonstrated high sensitivity and specificity in detecting COVID-19 from CXR images.
- Visualizations provided insights into feature separability for COVID-19 detection.
Conclusions:
- The proposed deep learning fusion framework shows significant promise for automated COVID-19 diagnosis using CXR.
- This AI-driven approach can assist radiologists in faster and more accurate screening.
- Further validation on diverse datasets is warranted for clinical implementation.
