Related Experiment Video
Updated: Oct 4, 2025
04:48
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022
3.0K
Complex features extraction with deep learning model for the detection of COVID19 from CT scan images using ensemble
Md Robiul Islam1, Md Nahiduzzaman1
1Department of Electrical & Computer Engineering, Rajshahi University of Engineering & Technology, Rajshahi 6204, Bangladesh.
Expert Systems with Applications
|February 9, 2022
Summary
This study introduces a new Convolutional Neural Network (CNN) model for detecting COVID-19 from CT scans. The model achieves high accuracy, offering a faster alternative to RT-PCR for COVID-19 diagnosis.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Infectious Diseases
Background:
- The novel Coronavirus disease (COVID-19) is a highly infectious disease impacting global public health.
- Reverse transcription-polymerase chain reaction (RT-PCR) for COVID-19 detection is time-consuming and prone to errors.
- Computed Tomography (CT) imaging presents a potential alternative for rapid COVID-19 detection.
Purpose of the Study:
- To develop an efficient and accurate method for COVID-19 detection using CT images.
- To enhance CT image quality for better feature extraction.
- To compare the performance of a novel Convolutional Neural Network (CNN) model against existing methods.
Main Methods:
- Contrast Limited Histogram Equalization (CLAHE) was applied for CT image preprocessing and enhancement.
- A novel CNN model was developed to extract 100 prominent features from 2482 CT images.
- Extracted features were classified using Gaussian Naive Bayes (GNB), Support Vector Machine (SVM), Decision Tree (DT), Logistic Regression (LR), and Random Forest (RF).
- An ensemble model was proposed for COVID-19 CT image classification.
Main Results:
- The proposed ensemble model achieved superior performance compared to state-of-the-art methods.
- The model attained an accuracy of 99.73%, precision of 99.46%, and recall of 100% in COVID-19 classification.
- Feature extraction using the CNN model effectively identified key indicators in CT scans.
Conclusions:
- The developed ensemble model demonstrates high efficacy and accuracy for COVID-19 detection from CT images.
- This AI-driven approach offers a promising, rapid, and reliable alternative to traditional diagnostic methods.
- The study highlights the potential of advanced machine learning techniques in managing infectious disease outbreaks.
