Automatic detection of the meningioma tumor firmness in MRI images
Related Experiment Video
Updated: Dec 18, 2025
Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging
Published on: December 15, 2014
Atheer AlKubeyyer1, Mohamed Maher Ben Ismail1, Ouiem Bchir1
1Computer Science Department, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia.
Abstract:
Meningioma is among the most common primary tumors of the brain. The firmness of Meningioma is a critical factor that influences operative strategy and patient counseling. Conventional methods to predict the tumor firmness rely on the correlation between the consistency of Meningioma and their preoperative MRI findings such as the signal intensity ratio between the tumor and the normal grey matter of the brain. Machine learning techniques have not been investigated yet to address the Meningioma firmness detection problem. The main purpose of this research is to couple supervised learning algorithms with typical descriptors for developing a computer-aided detection (CAD) of the Meningioma tumor firmness in MRI images. Specifically, Local Binary Patterns (LBP), Gray Level Co-occurrence Matrix (GLCM) and Discrete Wavelet Transform (DWT) are extracted from real labeled MRI-T2 weighted images and fed into classifiers, namely support vector machine (SVM) and k-nearest neighbor (KNN) algorithm to learn association between the visual properties of the region of interest and the pre-defined firm and soft classes. The learned model is then used to classify unlabeled MRI-T2 weighted images. This paper represents a baseline comparison of different features used in CAD system that intends to accurately recognize the Meningioma tumor firmness. The proposed system was implemented and assessed using a clinical dataset. Using LBP feature yielded the best performance with 95% of F-score, 87% of balanced accuracy and 0.87 of the area under ROC curve (AUC) when coupled with KNN classifier, respectively.
Insights
This study introduces a machine learning approach to predict brain tumor (meningioma) firmness using MRI images. Local Binary Patterns with a k-nearest neighbor classifier achieved 95% accuracy, aiding surgical planning.
Area of Science:
- Neurosurgery
- Medical Imaging
- Machine Learning
Background:
- Meningioma is a common brain tumor where firmness impacts surgical decisions.
- Current methods predict firmness using MRI signal ratios, but machine learning has not been applied.
- Accurate prediction of meningioma firmness is crucial for operative strategy and patient care.
Purpose of the Study:
- To develop a computer-aided detection (CAD) system for meningioma firmness using supervised learning algorithms.
- To compare the effectiveness of different image features (LBP, GLCM, DWT) for firmness detection.
- To investigate the use of Support Vector Machine (SVM) and k-nearest neighbor (KNN) classifiers.
Main Methods:
- Extracted Local Binary Patterns (LBP), Gray Level Co-occurrence Matrix (GLCM), and Discrete Wavelet Transform (DWT) features from MRI-T2 weighted images.
- Trained SVM and KNN classifiers on labeled images to associate visual properties with tumor firmness (firm/soft).
- Validated the model on a clinical dataset to classify unlabeled meningioma images.
Main Results:
- The system utilizing LBP features with the KNN classifier demonstrated superior performance.
- Achieved a 95% F-score, 87% balanced accuracy, and an Area Under the ROC Curve (AUC) of 0.87.
- This indicates a highly effective method for recognizing meningioma tumor firmness.
Conclusions:
- Machine learning, particularly using LBP features with KNN, offers a promising approach for detecting meningioma firmness from MRI.
- The developed CAD system provides a non-invasive tool to aid in surgical planning and patient management.
- This research establishes a baseline for machine learning applications in predicting meningioma consistency.
More Related Videos
12:50Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly
Published on: April 14, 2014
10:25Author Spotlight: Integrating High-Resolution Intravital Imaging and MRI to Enhance Stereotactic Body Radiation Therapy Planning
Published on: April 12, 2024
