A Classification Algorithm by Combination of Feature Decomposition and Kernel Discriminant Analysis (KDA) for Automatic MR Brain Image Classification and AD Diagnosis

Table 2

Results comparison of the feature decomposition, KDA, and also the proposed technique for classification of pMCI vs. NC.

Methods	ACC (%)	SEN (%)	SPE (%)	AUC (%)
Feature decomposition	82.68	76.9	86.88	83.59
KDA	72.59	55.88	84.78	77.91
Proposed method	84.29	90.4	79.85	83.54