A Hybrid Alzheimer's Stage Classifier by Kernel SVM, MLP Using Texture and Statistical Features of Brain MRI

摘要

Alzheimer's Sisease (AD) stage classification is carried on 54 numbers of T2-weighted Magnetic resonance Images of different stages. Statistical and textual features collected from Segments of white, gray matter, and cerebral spinal fluid forms as a data frame. Classification of the data is carried by Kernel Support vector machines and multilayer perceptron algorithm. Its result is compared with the proposed classifier using Area Under Curve (AUC), Classification Accuracy (CA), Fl, Precision, and Recall. It is observed that Linear Kernel SVM gives 96.29% of classification accuracy. But Hybrid KSVM classification accuracy is increased to 100%.