Related Experiment Video
Updated: Sep 8, 2025
03:38
Unilateral Lung Volume Analysis Using Micro-CT for Enhanced Assessment of Pulmonary Fibrosis in Preclinical Models
Published on: June 20, 2025
322
Ensemble Learning Framework with GLCM Texture Extraction for Early Detection of Lung Cancer on CT Images
Sara A Althubiti1, Sanchita Paul2, Rajanikanta Mohanty3
1Department of Computer Science, College of Computer and Information Sciences, Majmaah University, Al-Majmaah, Saudi Arabia.
Computational and Mathematical Methods in Medicine
|June 13, 2022
Summary
This study enhances lung cancer detection using computer-assisted diagnosis on CT scans. Fuzzy c-means clustering achieved 98% accuracy, significantly improving early diagnosis capabilities.
Area of Science:
- Medical Imaging
- Artificial Intelligence in Oncology
- Computer-Aided Diagnosis
Background:
- Lung cancer is a leading global cause of mortality, with early detection crucial for improving patient outcomes.
- Diagnosing lung cancer from computerized tomography (CT) scans remains challenging, necessitating advanced computational methods.
- Computer-assisted diagnosis (CAD) systems offer a promising approach to enhance the accuracy and efficiency of cancer detection.
Purpose of the Study:
- To evaluate the effectiveness of various image preprocessing techniques and clustering algorithms for lung cancer detection in CT images.
- To compare the performance of fuzzy c-means and k-means clustering for optimizing lung CT image analysis.
- To assess the accuracy of different classification algorithms, including gradient boosting, for computer-assisted lung cancer diagnosis.
Main Methods:
- Preprocessing of 20 lung CT scan images using median filters and adaptive histogram equalization to enhance image quality.
- Application and comparison of fuzzy c-means and k-means clustering algorithms for image segmentation and optimization.
- Feature extraction using the Gray Level Co-occurrence Matrix (GLCM) followed by classification using bagging, gradient boosting, and ensemble methods.
Main Results:
- The median filter was identified as the most effective preprocessing filter for lung CT images.
- Fuzzy c-means clustering demonstrated superior performance with an accuracy of 98% compared to k-means.
- Gradient boosting achieved the highest classification accuracy of 90.9% among the evaluated algorithms.
Conclusions:
- Computer-assisted diagnosis, particularly employing fuzzy c-means clustering and gradient boosting, significantly enhances the accuracy of lung cancer detection from CT scans.
- The study highlights the potential of advanced image processing and machine learning techniques to improve early lung cancer diagnosis.
- Optimized CAD systems can aid radiologists in making more precise and timely diagnoses, potentially saving lives.
