Related Experiment Video
Updated: Feb 20, 2026
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
Published on: April 13, 2013
Automatic selection of localized region-based active contour models using image content analysis applied to brain
Elisee Ilunga-Mbuyamba1, Juan Gabriel Avina-Cervantes1, Jonathan Cepeda-Negrete2
1Telematics (CA), Engineering Division (DICIS), Campus Irapuato-Salamanca, University of Guanajuato, Carr. Salamanca-Valle de Santiago km 3.5 + 1.8km, Comunidad de Palo Blanco, Salamanca, 36885, Gto., Mexico.
This study introduces an automated framework for selecting the best localized region-based active contour model (LRACM) for brain tumor segmentation from MRI images. The system improves segmentation accuracy by intelligently choosing between LGDF, C-V, and LACM-BIC methods based on image content.
Area of Science:
- Medical Image Analysis
- Computational Imaging
- Artificial Intelligence in Medicine
Background:
- Manual brain tumor segmentation is time-consuming and labor-intensive.
- Automatic segmentation methods are crucial for efficient clinical workflows.
- Existing localized region-based active contour models (LRACMs) have limitations.
Purpose of the Study:
- To develop an automated framework for selecting the optimal LRACM for brain tumor segmentation.
- To improve the accuracy and efficiency of brain tumor segmentation in MRI images.
- To address the variability in performance among different LRACM techniques.
Main Methods:
- Proposed a supervised framework for automatic LRACM selection.
- Extracted twelve visual features from input images to guide method selection.
- Evaluated the framework on three LRACMs: Local Gaussian Distribution Fitting (LGDF), localized Chan-Vese (C-V), and Localized Active Contour Model with Background Intensity Compensation (LACM-BIC).
- Applied the system to Magnetic Resonance Imaging (MRI) data.
Main Results:
- The proposed system demonstrated the ability to correctly select the most suitable LRACM for a given MRI image.
- The automated selection framework achieved superior accuracy compared to using any of the three LRACMs individually.
- The system effectively leverages image content for informed method selection.
Conclusions:
- An intelligent framework for automatic LRACM selection can significantly enhance brain tumor segmentation accuracy.
- This approach offers a more robust and efficient solution for clinical applications.
- The proposed method provides a valuable tool for improving diagnostic and treatment planning processes in neuro-oncology.
