A Semisupervised Learning Scheme with Self-Paced Learning for Classifying Breast Cancer Histopathological Images

Table 7

Precision (Prec.), recall (R), and F1-score (F1) values for multiclass classification.

Mag. factor	% of Pseudolabels	Prec. (%)	R (%)	F1 (%)
40X	(top-5%)	94.96	94.71	94.67
	(top-10%)	95.15	94.78	94.80
	(top-20%)	94.63	94.55	94.59
	All pseudolabels	93.25	93.0	93.21
100X	(top-5%)	91.85	91.71	91.89
	(top-10%)	93.14	92.85	92.38
	(top-20%)	94.24	94.71	94.33
	All pseudolabels	90.63	90.39	90.51
200X	(top-5%)	95.85	95.90	95.56
	(top-10%)	95.47	94.91	95.32
	(top-20%)	91.44	91.07	91.64
	All pseudolabels	92.65	92.0	92.75
400X	(top-5%)	93.48	93.23	93.51
	(top-10%)	94.36	94.28	94.38
	(top-20%)	92.69	92.14	92.32
	All pseudolabels	90.63	90.57	90.41