表 2. Comparison of segmentation results evaluation of different models ().

不同模型的分割结果评估对比（）

方法	DSC	IoU	VOE	RVD	SP	SE	PC
U-Net	0.935 ± 0.007	0.879 ± 0.012	0.065 ± 0.015	0.067 ± 0.017	0.972 ± 0.010	0.957 ± 0.017	0.916 ± 0.030
SegNet	0.909 ± 0.009	0.834 ± 0.016	0.123 ± 0.056	0.134 ± 0.061	0.948 ± 0.014	0.969 ± 0.019	0.858 ± 0.032
U-Net++	0.930 ± 0.012	0.870 ± 0.021	0.057 ± 0.039	0.060 ± 0.043	0.968 ± 0.011	0.958 ± 0.007	0.905 ± 0.028
U-Net3+	0.912 ± 0.013	0.838 ± 0.021	0.132 ± 0.028	0.334 ± 0.316	0.947 ± 0.010	0.976 ± 0.003	0.856 ± 0.023
DeepLabv3+	0.937 ± 0.003	0.881 ± 0.006	0.060 ± 0.017	0.063 ± 0.019	0.969 ± 0.004	0.966 ± 0.006	0.910 ± 0.010
DSPA-Net	0.972 ± 0.002	0.945 ± 0.004	0.012 ± 0.002	0.012 ± 0.002	0.989 ± 0.001	0.977 ± 0.001	0.966 ± 0.003