Table 4.

Results on the validation set from dataset 1. Results are presented as mean ± standard error of the mean across the dataset. Volume Error Rate denoted as VER, absolute VER denoted as AVER. Best performances are denoted in bold face.

Method	Data Augmentation	Dice	Recall	Precision	VER	AVER	Pearson r
1-step	no	0.73 ± 0.01	0.73 ± 0.02	0.75 ± 0.02	0.04 ± 0.05	0.16 ± 0.03	0.76
	yes	0.71 ± 0.01	0.70 ± 0.02	0.74 ± 0.02	0.08 ± 0.04	0.16 ± 0.03	0.82
2-step	no	0.73 ± 0.01	0.70 ± 0.02	0.76 ± 0.02	0.11 ± 0.05	0.18 ± 0.04	0.73
	yes	0.70 ± 0.01	0.68 ± 0.02	0.74 ± 0.01	0.12 ± 0.04	0.16 ± 0.03	0.86