Related Experiment Video
Updated: Dec 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
14.6K
Classification of COVID-19 patients from chest CT images using multi-objective differential evolution-based
Dilbag Singh1, Vijay Kumar2, Vaishali3
1Computer Science and Engineering Department, School of Computing and Information Technology, Manipal University Jaipur, Jaipur, India.
Summary
Automated analysis of chest CT scans using convolutional neural networks (CNNs) offers a rapid and accurate method for classifying COVID-19 infections. This approach aids in early disease detection and management, especially during rapid outbreaks.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Infectious Disease Diagnostics
Background:
- Early classification of COVID-19 is crucial for effective treatment and containment.
- Chest CT imaging presents a rapid and reliable alternative to RT-PCR for COVID-19 assessment.
- Manual interpretation of CT scans is time-consuming and requires expert radiologists.
Purpose of the Study:
- To develop an automated system for classifying COVID-19 patients using chest CT images.
- To enhance the speed and efficiency of COVID-19 diagnosis through artificial intelligence.
- To reduce the workload on medical professionals during high-infection periods.
Main Methods:
- Utilized convolutional neural networks (CNNs) for automated classification of chest CT images.
- Optimized CNN initial parameters using multi-objective differential evolution (MODE).
- Evaluated the proposed model against competitive machine learning techniques.
Main Results:
- The proposed CNN model demonstrated a good accuracy rate in classifying COVID-19 positive and negative cases from chest CT images.
- Automated analysis significantly reduces the time required for classification compared to manual expert review.
- The MODE-tuned CNN model showed competitive performance in classifying chest CT scans.
Conclusions:
- Automated chest CT image analysis using CNNs is a viable and effective tool for rapid COVID-19 classification.
- The developed AI model can assist healthcare professionals in timely diagnosis and patient management.
- This technology holds significant potential for supporting public health responses during infectious disease epidemics.
