Table 4.

Segmentation quantitative performance for the two models with and without deep supervision (DS).

Method/evaluation	Dice score	Precision	Recall	F1 score	Processing time (s)
Without DS	0.79 ± 0.11	0.81 ± 0.09	0.77 ± 0.09	0.74	0.72 ± 0.10
With DS	0.84 ± 0.06	0.85 ± 0.07	0.83 ± 0.07	0.84	0.74 ± 0.07