Related Experiment Video
Updated: Nov 7, 2025
04:17
DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
Published on: May 10, 2024
1.1K
Medical image-based detection of COVID-19 using Deep Convolution Neural Networks
Loveleen Gaur1, Ujwal Bhatia1, N Z Jhanjhi2
1Amity International Business School, Amity University, Noida, India.
Multimedia Systems
|May 3, 2021
Summary
This study developed a deep learning model using chest X-rays for accurate COVID-19 detection. The system effectively distinguishes COVID-19 from viral pneumonia and normal cases, aiding rapid screening.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Computer Vision
Background:
- Increasing global demand for automated COVID-19 detection.
- Healthcare systems are burdened by the exponential rise in COVID-19 cases.
- Exploration of multimedia healthcare data for diagnostic solutions.
Purpose of the Study:
- To develop a practical solution for COVID-19 detection from chest X-rays.
- To differentiate COVID-19 cases from normal and viral pneumonia.
- To evaluate the efficacy of Deep Convolutional Neural Networks (CNNs) for this task.
Main Methods:
- Utilized three pre-trained CNN models: EfficientNetB0, VGG16, and InceptionV3.
- Employed transfer learning techniques for model training and evaluation.
- Leveraged a publicly available dataset compiled from diverse sources.
Main Results:
- Achieved an overall accuracy of 92.93% for COVID-19 detection.
- Demonstrated a high sensitivity of 94.79% for identifying COVID-19 cases.
- Evaluated model performance using standard metrics like accuracy, recall, precision, and F1 scores.
Conclusions:
- The proposed deep learning approach provides a high-quality model for COVID-19 detection.
- Computer vision designs show significant potential for effective screening and early detection measures.
- The selected CNN models offer a balance of accuracy and efficiency suitable for mobile applications.
