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

Table 5

Average results on the 3D feature extraction model for various classifiers on real-time 320 patient data volumes.

Classifier	Specificity %	Sensitivity %	Accuracy %	ROC ()	Mean square error
BPN [17]	68.17	89.58	88.85	0.89	0.21
NN [17]	76.19	91.84	91.14	0.93	0.10
Developed SVM classifier	95.0	98.94	98.4	0.99	0.015