Table 2. Diagnostic performances of different classification models through microcalcification features (15 features).

	Test Dataset				Training Dataset
	accuracy	sensitivity	specificity	AUC	mean ± std (Accuracy)
SVM	85.8%	0.93	0.79	0.85	0.79 ± 0.07
KNN (N = 8)	83.8%	0.95	0.74	0.84	0.77 ± 0.07
LDA	58.8%	0.63	0.55	0.59	0.61 ± 0.05
SAE	87.3%	0.93	0.82	0.87	0.82 ± 0.05

The proposed SAE achieved superior performance in terms of the four measurements. The best measurements were highlighted in bold.