Table 6. Different evaluation scores calculated for SVM with different kernel functions for the CBIS-DDSM dataset.

Numbers in red indicate the best values between the several techniques.

SVM Kernel functions	CBIS-DDSM dataset
	Accuracy	AUC	Sensitivity	Specificity	Precision	F1 score
Linear	86.8%	0.94	0.854	0.876	0.88	0.866
Quadratic	85.6%	0.93	0.851	0.858	0.86	0.855
Cubic	84.6%	0.92	0.841	0.848	0.85	0.845
Fine Gaussian	69.9%	0.82	0.63	0.851	0.92	0.747
Medium Gaussian	87.2%	0.94	0.862	0.877	0.88	0.871
Coarse Gaussian	86.2%	0.93	0.854	0.876	0.88	0.866