Table 6.

Results on the Consensus-based Gold Standard dataset (150 images): (top) performance of BS-Net (ENS) computed on the Consensus-based Gold Standard; (center) performance of BS-Net (HS) vs. original rater $R_0$; (bottom) averaged performance of all $R_i$ vs. CbGS

	MEr	MAE	SD	CC
	BS-Net (ENS) vs. CbGS
Avg. on reg.	$-$0.133	0.424	0.580	0.743
Global score	0.800	1.787	1.354	0.907
	BS-Net (ENS) vs. $R_0$
Avg. on reg.	$-$0.019	0.452	0.575	0.754
Global score	$-$0.113	1.847	1.553	0.834
	Average on all pairs of radiologists
Avg. on reg.	$-$0.131	0.528	0.614	0.736
Global score	$-$0.784	2.592	1.965	0.835