Multi Class Brain Cancer Prediction System Empowered with BRISK Descriptor

Magnetic Resonance Imaging (MRI) is one of the important resources for identifying abnormalities in human brain. This work proposes an effective Multi-Class Classification (MCC) system using Binary Robust Invariant Scalable Keypoints (BRISK) as texture descriptors classification. At first, potential Region Of Interests (ROIs) are detected features from accelerated segment test algorithm. Then, non-maxima suppression employed scale space based on information ROIs. The discriminating power BRISK examined three machine learning classifiers such k-Nearest Neighbour (kNN), Support Vector Machine (SVM) and Random Forest (RF). An MCC developed which classifies MRI images into normal, glioma, meningioma pituitary. A total 3264 brain this study to evaluate proposed system. Results show that average accuracy MCC-RF 99.62% with a sensitivity 99.16% specificity 99.75%. MCC-kNN 93.65% 97.59% by MCC-SVM