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

Table 5

Results of the proposed method comparison and other methods for AD vs. NC.

Methods	ACC (%)	SEN (%)	SPE (%)	AUC (%)
LDA	87.60	82.89	91.64	92.89
SRC [5]	87.83	80.84	93.85	89.77
[5]	84.57	72.82	94.76	91.40
Proposed method	90.41	84.37	95.63	93.83