A Deep-Learning Model with Learnable Group Convolution and Deep Supervision for Brain Tumor Segmentation

Table 2

Comparison of the proposed network model and typical methods.

Model	(M)	(G)	Dice (%)			Hausdorff (mm)
			Et	Wt	Tc	Et	Wt	Tc
DLSDNet	5.23	36.14	80.36	90.25	86.20	2.78	4.47	5.74
3D U-Net [27]	16.21	1669.53	75.96	88.53	71.77	6.04	17.10	11.62
3D-ESPNet [29]	3.63	76.51	73.70	88.30	81.40	—	—	—
Kao et al. [30]	9.45	203.96	78.75	90.47	81.35	3.81	4.32	7.56
No New-Net [31]	10.36	202.25	81.01	90.83	85.44	2.41	4.27	6.52
NVDLMED [32]	40.06	1495.53	81.73	90.68	86.02	3.82	4.52	6.85