Related Experiment Video
Updated: Aug 26, 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
Towards edge devices implementation: deep learning model with visualization for COVID-19 prediction from chest X-ray.
Shaline Jia Thean Koh1, Marwan Nafea1, Hermawan Nugroho1
1Present Address: Department of Electrical and Electronic Engineering, University of Nottingham Malaysia, Semenyih, 43500 Malaysia.
Advances in Computational Intelligence
|October 3, 2022
Summary
This study introduces a deep learning model for rapid COVID-19 diagnosis using chest X-rays on edge devices. The model achieves high accuracy and improves inference speed, enabling deployment in resource-limited settings.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Computer Science
Background:
- The COVID-19 pandemic necessitates rapid diagnostic tools, especially in resource-limited areas.
- Current diagnostic methods face challenges with accessibility and speed, particularly in rural settings.
- Radiological image analysis offers a potential avenue for swift COVID-19 detection.
Purpose of the Study:
- To develop an efficient and accurate COVID-19 diagnostic method using chest X-ray analysis.
- To enable the deployment of deep learning models for COVID-19 detection on edge devices.
- To improve diagnostic capabilities in primary care clinics and rural areas lacking stable internet.
Main Methods:
- Convolutional neural network (CNN) models were fine-tuned using transfer learning techniques.
- Chest X-ray images were analyzed to predict COVID-19 and pneumonia infections.
- Gradient Class Activation Map (Grad-CAM) was employed to visualize decision-making regions.
- The trained model was implemented on edge devices (NCS2) for performance evaluation.
Main Results:
- The developed model achieved a diagnostic accuracy of 98.13%, sensitivity of 97.7%, and specificity of 99.1%.
- Grad-CAM heat maps showed strong correlation with clinical evidence identified by radiologists.
- Edge device implementation resulted in a 90% improvement in inference speed compared to CPU.
Conclusions:
- The proposed deep learning approach offers an efficient and accurate method for COVID-19 diagnosis from chest X-rays.
- Deployment on edge devices enhances diagnostic capabilities in remote and underserved areas.
- The model's performance and speed make it suitable for practical applications in primary care settings.
