Research Article

Image Analysis for MRI Based Brain Tumor Detection and Feature Extraction Using Biologically Inspired BWT and SVM

Table 7

Comparison of accuracies in different classifiers.

⁢Number of test images (normal = 67, abnormal = 134)
Evaluation parameter ANFIS Back Propagation Proposed classifier (SVM) -NN

True negative 63 62 65 63
False positive 16 19 4 18
True positive 118 110 129 112
False negative 4 10 3 8
Specificity (%) 79.74 76.54 94.2 77.77
Sensitivity (%) 96.72 97.5 97.72 93.33
Accuracy (%) 90.04 85.57 96.51 87.06