Detecting Brain Tumor using Machines Learning Techniques Based on Different Features Extracting Strategies.

Area of Science:

• Medical Imaging
• Machine Learning
• Computational Biology

Background:

• Brain tumors are a leading global cause of death.
• Early detection and classification of brain tumors are crucial for improving survival rates.
• Magnetic Resonance Imaging (MRI) is a key tool for brain tumor detection.

Purpose of the Study:

• To enhance brain tumor detection performance.
• To propose a multimodal feature extraction strategy.
• To employ advanced machine learning techniques for improved diagnostic accuracy.

Main Methods:

• Extracted multimodal features: texture, morphological, entropy-based, Scale Invariant Feature Transform (SIFT), and Elliptic Fourier Descriptors (EFDs).
• Utilized machine learning classifiers: Support Vector Machine (SVM), Decision Tree (DT), and Naïve Bayes.
• Performed validation using 10-fold Cross-Validation (CV).

Main Results:

• Naïve Bayes classifier achieved 100% accuracy (Specificity, Sensitivity, PPV, NPV, TA, AUC) using entropy, morphological, SIFT, and texture features.
• Decision Tree and SVM polynomial kernel also demonstrated high performance (TA up to 97.81% and 94.63%, respectively).
• High statistical significance was observed with SVM polynomial and RB kernels for texture features.

Conclusions:

• Naïve Bayes and Decision Tree classifiers offer superior detection accuracy for brain tumors.
• The proposed multimodal feature extraction strategy significantly improves diagnostic performance.
• This approach holds promise for more effective Computer-Aided Diagnosis (CAD) systems.