Related Experiment Video
Updated: Oct 4, 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
14.4K
COVID-19 detection from chest x-ray using MobileNet and residual separable convolution block
V Santhosh Kumar Tangudu1, Jagadeesh Kakarla1, Isunuri Bala Venkateswarlu1
1Indian Institute of Information Technology, Design and Manufacturing, Kancheepuram, Chennai, India.
Soft Computing
|February 2, 2022
Summary
This study introduces an efficient deep learning model for rapid COVID-19 detection using chest X-rays. The novel approach achieves 99% accuracy with reduced training time, aiding early diagnosis.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Infectious Diseases
Background:
- The COVID-19 pandemic significantly impacts global health and economies.
- Early detection of COVID-19 is crucial for patient survival.
- Chest radiography offers a rapid and cost-effective diagnostic method.
Purpose of the Study:
- To develop an automated COVID-19 detection system using chest X-ray images.
- To address the high training time limitations of existing deep learning models.
- To improve the accuracy and efficiency of COVID-19 diagnosis.
Main Methods:
- Utilized transfer learning with a pre-trained MobileNet model.
- Introduced a novel residual separable convolution block to enhance MobileNet performance.
- Evaluated the model on two public datasets: COVID5K and COVIDRD.
Main Results:
- Achieved 99% accuracy in COVID-19 detection on both datasets.
- Demonstrated superior performance compared to existing state-of-the-art and pre-trained models.
- Maintained high performance on noisy datasets.
- Showcased reduced training time and fewer parameters compared to existing models.
Conclusions:
- The proposed model offers a highly accurate and efficient solution for automated COVID-19 detection from chest X-rays.
- The model's efficiency in terms of training time and parameters makes it suitable for mobile applications.
- This advancement can aid in faster and more accessible COVID-19 diagnosis globally.
