TABLE 3.

Experimental results on the ISIC2018-Task dataset.

Method	AC	PR	SP	Dice
U-Net (Ronneberger et al., 2015)	0.9446	0.8746	0.9671	0.8674
Att-UNet (Oktay et al., 2018)	0.9516	0.9075	0.9766	0.8820
U-Net++ (Zhou et al., 2018)	0.9517	0.9067	0.9764	0.8822
MultiResUNet (Ibtehaz and Rahman, 2020)	0.9473	0.8765	0.9704	0.8694
Residual U-Net (Diakogiannis et al., 2020)	0.9468	0.8753	0.9688	0.8689
TransUNet (Chen et al., 2021)	0.9452	0.8823	0.9653	0.8499
UCTransNet (Wang et al., 2022a)	0.9546	0.9100	0.9770	0.8898
MISSFormer (Huang et al., 2022)	0.9453	0.8964	0.9742	0.8657
MIPC-Net(ours)	0.9560	0.9279	0.9831	0.8875

The bold values indicate the best performance among all the methods compared in each respective evaluation metric. For each row in a table, the bold number represents the method that achieves the highest score or lowest error on that particular metric, demonstrating its superior performance relative to the other approaches.