Table 1.

Mean relative volume of segmentations produced by the different models as compared to the ground truth segmentations, both in the 70/30 and the 50/50 dataset split

Model	70/30		50/50
	Rel.vol.	p value	Rel.vol.	p value
Atlas	1.01	$>0.05$	1.00	$>0.05$
Siemens	1.04	$>0.05$	1.10	$3·{10}^{-4}$
V-net	0.99	$>0.05$	0.99	$>0.05$
TL	0.96	$6·{10}^{-4}$	0.93	$3·{10}^{-7}$
GAN	0.96	$1·{10}^{-3}$	0.98	$>0.05$
Eff.Det3D	0.98	$>0.05$	1.01	$>0.05$

A value above one means that the model tends to overestimate the volume and vice versa. The p-values indicate how significant the (signed) volume difference is (Wilcoxon signed-rank test)