Related Experiment Video
Updated: Sep 22, 2025
08:05
Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
Published on: December 19, 2020
14.3K
A COVID-19 CXR image recognition method based on MSA-DDCovidNet
Wei Wang1, Wendi Huang1, Xin Wang1
1School of Computer and Communication Engineering Changsha University of Science and Technology Changsha China.
IET Image Processing
|May 23, 2022
Summary
A new deep learning model, MSA-DDCovidNet, accurately detects COVID-19 in chest X-rays with 97.962% accuracy. This lightweight model offers faster and more precise diagnoses for coronavirus disease 2019 (COVID-19).
Area of Science:
- Artificial Intelligence
- Medical Imaging
- Deep Learning
Background:
- Coronavirus disease 2019 (COVID-19) remains a global health challenge.
- Chest X-ray (CXR) imaging is a crucial tool for diagnosing respiratory illnesses.
- Deep learning offers potential for automated analysis of medical images.
Purpose of the Study:
- To develop a highly accurate and efficient deep learning model for COVID-19 detection using CXR images.
- To introduce novel modules for effective feature extraction from CXR data.
- To create a lightweight model suitable for rapid clinical deployment.
Main Methods:
- Designed MSA-DDCovidNet, a lightweight convolutional neural network.
- Utilized the dual-path multi-scale fusion (DMFF) module for shallow feature extraction.
- Employed the dense dilated depth-wise separable (D3S) module for deep feature extraction.
- Integrated a multi-scale spatial attention (MSA) mechanism to enhance feature representation.
Main Results:
- Achieved a high accuracy of 97.962% in detecting COVID-19 from CXR images.
- Demonstrated reduced computational complexity and fewer parameters compared to existing methods.
- Validated the model's effectiveness in identifying infected individuals through CXR analysis.
Conclusions:
- MSA-DDCovidNet provides a safe, effective, and accurate method for COVID-19 detection.
- The model's lightweight nature and high accuracy facilitate quicker and more precise diagnoses.
- This deep learning approach shows significant promise for improving COVID-19 screening protocols.
