Table 2.

Contribution of subview prediction (implicit training).

Dataset	Method	Sp (%)	Se (%)	GMean (%)	Acc (%)	AUC	NPV = 95%
							TPR (%)	FPR (%)
DS1	Simple	91.74	73.25	81.97	86.40	0.9047	64.482	8.368
	Subview	92.58	73.52	82.50	87.08	0.9149	71.202	9.239
DS2	Simple	91.73	76.51	83.77	87.30	0.9228	75.336	9.680
	Subview	92.45	76.40	84.04	87.78	0.9318	80.983	10.405
DS3	Simple	89.30	74.65	81.64	85.10	0.9030	70.424	9.232
	Subview	90.23	74.88	82.20	85.84	0.9112	74.256	9.735
DS4	Simple	87.31	82.30	84.77	84.49	0.9131	0	0
	Subview	88.15	82.30	85.18	84.85	0.9192	0	0
DS5	Simple	85.80	82.18	83.97	83.79	0.9067	0	0
	Subview	86.78	82.34	84.53	84.31	0.9135	0	0
DS6	Simple	86.98	81.30	84.09	83.90	0.9098	0	0
	Subview	88.21	81.60	84.84	84.62	0.9168	0	0
DS7	Simple	83.71	80.09	81.88	81.89	0.8872	0.045	0.012
	Subview	84.19	80.46	82.30	82.31	0.8943	0	0
DS8	Simple	83.53	80.40	81.95	81.87	0.8891	0.101	0.013
	Subview	84.79	80.97	82.86	82.77	0.8962	0.032	0.004
DS9	Simple	87.07	71.34	78.81	82.51	0.8635	0	0
	Subview	87.24	70.91	78.65	82.51	0.8733	0	0