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

Table 7

Results of the proposed method compared with other techniques for pMCI vs. sMCI.

Methods	ACC (%)	SEN (%)	SPE (%)	AUC (%)
LDA	63.31	63.04	70.84	65.80
SRC [5]	64.68	63.87	65.21	66.18
[5]	64.08	74.35	56.59	69.94
Proposed method	65.94	81.44	54.69	71.02^1

¹It would be a radial basis (BF) kernel SVM.