Hybrid RGSA and Support Vector Machine Framework for Three-Dimensional Magnetic Resonance Brain Tumor Classification

Table 6

Performance analysis of classifiers and feature extraction, both 2D and 3D.

Texture analysis	Classifier	Accuracy % w/o feature selection	Accuracy % with feature selection
	BPN	72.45	81.2
2D GLCM + 2D RUN LENGTH + 2D SGLDM [25]	NN	84.34	89.45
	SVM	89.55	91.02
Proposed 3D GLCM + 3D RUN LENGTH + 3D SGLDM	BPN	81.65	88.85
	NN	89.55	91.14
	SVM	90.78	98.4