Related Experiment Video
Updated: Jul 23, 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
14.2K
Automatic Diagnosis of COVID-19 Pneumonia using Artificial Intelligence Deep Learning Algorithm Based on Lung
Mohammad Amiri1, Manizheh Ranjbar2, Gholamreza Fallah Mohammadi3
1Assistant Professor, Department of Computer Engineering, Technical and Vocational University, Tehran, Iran.
Journal of Medical Signals and Sensors
|July 14, 2023
Summary
This study introduces an AI-powered software using deep learning on lung CT scans for accurate COVID-19 diagnosis. The developed tool achieves high accuracy, offering a promising clinical diagnostic solution for the pandemic.
Area of Science:
- Artificial Intelligence
- Medical Imaging
- Deep Learning
Background:
- Lung computed tomography (CT) scans offer crucial data for early COVID-19 diagnosis.
- Image processing software leveraging AI can aid in identifying COVID-19 patterns.
- The global pandemic necessitated advanced diagnostic tools for rapid detection.
Purpose of the Study:
- To design and validate an AI-based software for accurate COVID-19 diagnosis using lung CT scans.
- To enhance the diagnostic capabilities of image processing software through deep learning.
- To provide a clinically applicable tool for early COVID-19 detection.
Main Methods:
- A convolutional neural network (CNN) architecture based on Inception-V3 was employed for deep learning.
- Transfer learning was utilized to improve the system's learning capacity.
- Network layers were modified to enhance detection power, with learning repeated 30 times.
Main Results:
- The software demonstrated high diagnostic accuracy, sensitivity, and validity at 98% on data from Imam Khomeini Hospital.
- Certain diagnostic parameters achieved 100% accuracy on specific datasets.
- The modified Inception-V3 algorithm showed acceptable precision when applied to heterogeneous data.
Conclusions:
- The Inception-V3 based AI software exhibits effective speed and accuracy in diagnosing COVID-19 pneumonia from lung CT scans.
- The tool is a powerful diagnostic aid with potential for clinical application.
- This AI-driven approach supports early and accurate identification of COVID-19.
