Classification of Hematoxylin and Eosin-Stained Breast Cancer Histology Microscopy Images Using Transfer Learning with EfficientNets

Table 6

Specificity (spec.) and sensitivity (sens.) of the EfficientNet models.

Model	Normal		Benign		In situ		Invasive
	Spec. (%)	Sens. (%)	Spec. (%)	Sens. (%)	Spec. (%)	Sens. (%)	Spec. (%)	Sens. (%)
B0 (R)	93.33	93.33	87.0	93.33	100	6.7	93.75	100
B1 (R)	92.86	86.7	93.75	100	3.3	93.3	100	100
B2 (R)	93.5	100	100	100	00	93.3	100	100
B3 (M)	100	6.67	86.67	86.7	93.75	100	93.75	100
B4 (R)	100	6.67	92.86	86.7	83.33	100	3.33	93.3
B5 (N)	100	0.00	92.86	86.7	83.33	100	93.75	100
6 (N)	93.33	93.33	87.50	93.33	93.3	93.33	100	93.33