TABLE A1.

mIOU evaluation index of multi-class medical image segmentation.

Model	mIOU
	DSB2018	Lung	Eye blood vessels	ISBI2015	Liver cancer	Intestinal cancer
UNet (Ronneberger et al., 2015)	0.9078	0.9691	0.8106	0.8020	0.9854	0.9641
LinkNet (Chaurasia and Culurciello, 2018)	0.8983	0.9166	0.7457	0.7711	0.9803	0.9279
U2Net (Qin et al., 2020)	0.9126	0.9732	0.8070	0.8031	0.9854	0.9609
UNet++ (Zhou et al., 2018, 2020)	0.9108	0.9697	0.8083	0.8023	0.9849	0.9733
UNet+++ (Huang et al., 2020)	0.9134	0.9715	0.8077	0.7995	0.9858	0.9707
PraNet (Fan et al., 2020)	0.9453	0.9897	0.8762	0.8862	0.9903	0.9801
PspNet (Zhao et al., 2017)	0.7892	0.9568	0.5464	0.4891	0.9667	0.9551
Deeplabv3+ (Chen et al., 2018)	0.7871	0.9661	0.5449	0.4890	0.9721	0.9623
FCN8 (Long et al., 2015)	0.9041	0.9815	0.6687	0.7172	0.9853	0.9645
MBFFNet	0.9132	0.9704	0.8127	0.8061	0.9884	0.9709