Improved U-Net3+ with stage residual for brain tumor segmentation

BMC Medical Imaging

Table 1 Segmentation effect of each model

Model Type	Params	ET Dice	WT Dice	TC Dice	SEN_ET	SEN_WT	SEN_TC
2DUnet [4]	39 M	72.34	86.22	73.77	77.80	85.81	71.47
2DUnet++ [6]	36 M	72.39	85.60	73.36	76.20	85.78	71.81
2DUnet3+ [7]	27 M	73.93	87.23	77.28	74.94	88.26	77.97
Swin transformer [19]	27 M	76.18	83.75	82.33	78.31	84.28	80.34
3DUnet [20]	4.1 M	67.12	87.37	73.52	65.35	89.01	80.62
3DVnet [11]	40 M	76.25	88.87	78.72	80.00	91.30	83.37
3DResUnet [9]	4.2 M	72.60	87.96	71.24	73.70	90.11	73.43
3DUnet + +	6.8 M	67.12	85.81	67.66	63.91	88.38	75.99
3Dunet3 +	5 M	72.41	86.89	73.53	72.74	90.94	76.60
3D_FRN_Unet3+	5 M	72.22	87.74	78.59	81.18	92.28	81.20
Ours	6.6 M	75.65	88.77	78.62	79.12	91.51	78.96

ISSN: 1471-2342