Table 4.

Segmentation accuracy on the leave-one-out (LOO) experiment and on the network fine-tuned on splits S2 and S3, for both Experiment-1 and Experiment-2. Each row reports the Dice coefficient separately for each testing dataset, as well as the average Dice for each test.

Test	T1	T2	T3	T4	T5	T6	Avg.
LOO	0.03	0.29	0.20	$1\times {10}^{-4}$	$1\times {10}^{-4}$	0.10	0.10
S1 - Exp. 1	-	0.31	0.31	-	0.16	-	0.26
S2 - Exp. 1	-	-	0.36	0.02	-	0.11	0.15
S1 - Exp. 2	-	0.28	0.33	-	0.15	-	0.25
S2 - Exp. 2	-	-	0.36	0.07	-	0.13	0.19