TABLE A3.

Dice loss with CE evaluation index for multi-class medical image segmentation.

Model	Dice Loss with CE
	DSB2018	Lung	Eye blood vessels	ISBI2015	Liver cancer	Intestinal cancer
UNet (Ronneberger et al., 2015)	0.1264	0.0548	0.2222	0.3310	0.0146	0.0377
LinkNet (Chaurasia and Culurciello, 2018)	0.1423	0.0714	0.3258	0.3822	0.0215	0.0779
U2Net (Qin et al., 2020)	0.1191	0.0471	0.2344	0.3327	0.0148	0.0411
UNet++ (Zhou et al., 2018, 2020)	0.1213	0.0547	0.2248	0.3202	0.0151	0.0276
UNet+++ (Huang et al., 2020)	0.1199	0.0514	0.2351	0.3331	0.0144	0.0307
PraNet (Fan et al., 2020)	0.0921	0.0321	0.1453	0.2145	0.0101	0.0219
PspNet (Zhao et al., 2017)	0.3046	0.0743	0.6231	0.8119	0.0351	0.0801
Deeplabv3+ (Chen et al., 2018)	0.3068	0.0565	0.6285	0.8169	0.0290	0.0792
FCN8 (Long et al., 2015)	0.1318	0.0350	0.4485	0.4874	0.0145	0.0407
MBFFNet	0.1303	0.0638	0.2545	0.3254	0.0130	0.0303