Related Experiment Video
Updated: Jun 28, 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
Enhanced lung cancer detection: Integrating improved random walker segmentation with artificial neural network and
Sneha S Nair1, V N Meena Devi1, Saju Bhasi2
1Department of Physics, Noorul Islam Centre for Higher Education, Kumarakovil, Kanyakumari District, Tamil Nadu, India.
Heliyon
|April 15, 2024
Summary
This study demonstrates that a random forest classifier achieves 99.6% accuracy in detecting lung cancer, significantly outperforming artificial neural networks for pulmonary nodule classification.
Area of Science:
- Medical Imaging
- Machine Learning
- Artificial Intelligence
Background:
- Medical image segmentation is challenging due to image multimodality.
- Early detection of pulmonary issues like nodules is critical to prevent spread.
Purpose of the Study:
- To enhance the reliability of pulmonary nodule classification using machine learning.
- To accurately identify and classify lung nodules as benign or malignant.
Main Methods:
- Utilized anisotropic diffusion filtering for noise reduction in medical images.
- Employed a modified random walk method for lung nodule region of interest extraction.
- Applied texture-based feature extraction and random forest/artificial neural network classifiers for nodule classification.
Main Results:
- A random forest classifier achieved 99.6% accuracy in lung cancer detection.
- An artificial neural network achieved 94.8% accuracy in lung cancer detection.
- The framework was validated using cross-validation on Lung Image Database Consortium CT scan data.
Conclusions:
- Machine learning and image processing offer significant diagnostic potential for lung cancer categorization.
- Accurate identification and classification of lung nodules are crucial for patient outcomes.
