Related Experiment Video
Updated: Jul 3, 2025
09:29
Live Imaging of Microtubule Dynamics in Glioblastoma Cells Invading the Zebrafish Brain
Published on: July 29, 2022
2.7K
Brain tumor classification: a novel approach integrating GLCM, LBP and composite features
G Dheepak1, Anita Christaline J1, D Vaishali1
1Department of Electronics & Communication Engineering, Faculty of Engineering and Technology, SRM Institute of Science and Technology, Vadapalani Campus, Chennai, TN, India.
Frontiers in Oncology
|February 14, 2024
Summary
This study introduces a novel method for brain tumor classification using Gray-Level Co-Occurrence Matrix (GLCM) and Local Binary Pattern (LBP) features. The approach achieves 99.84% accuracy, improving tumor identification and treatment planning.
Area of Science:
- Medical Image Analysis
- Computational Pathology
- Artificial Intelligence in Medicine
Background:
- Manual tumor image analysis is time-consuming and subjective.
- Accurate tumor classification is crucial for patient care and treatment planning.
- Existing methods may lack the precision needed for complex tumor identification.
Purpose of the Study:
- To develop an automated, quantitative method for classifying brain tumors (Glioma, Meningioma, Pituitary Tumor).
- To enhance feature extraction techniques for improved tumor detection and classification accuracy.
- To integrate novel interaction features for superior discriminative capability.
Main Methods:
- Utilized Gray-Level Co-Occurrence Matrix (GLCM) and Local Binary Pattern (LBP) features for quantitative tumor image analysis.
- Developed novel interaction features via the outer product of GLCM and LBP feature vectors.
- Incorporated aggregated, statistical, and non-linear features derived from GLCM, and employed a linear Support Vector Machine classifier.
Main Results:
- The integrated feature extraction method demonstrated high effectiveness on tumor image datasets.
- Achieved a superior accuracy rate of 99.84% in brain tumor classification.
- Interaction features significantly enhanced the discriminative capability of the extracted features.
Conclusions:
- The proposed methodology offers a significant advancement in brain tumor classification accuracy.
- The integration of GLCM and LBP features provides a comprehensive texture representation.
- This approach holds substantial potential for improving diagnostic precision and clinical treatment planning.
