Skip to main content

Table 4 Ablation studies of different models on the ISIC2018 dataset. “\(\checkmark\)” indicates that the corresponding module has been added to the current model and “-” indicates that the corresponding module has not been added to the current model

From: iU-Net: a hybrid structured network with a novel feature fusion approach for medical image segmentation

Model

En-1

En-2

De

T-Up

W-FFM

Dice(%)

IoU(%)

Precision(%)

Recall(%)

1

\(\checkmark\)

-

\(\checkmark\)

-

-

87.87

80.67

94.70

86.07

2

\(\checkmark\)

\(\checkmark\)

\(\checkmark\)

-

-

89.16

81.92

94.37

86.78

3

\(\checkmark\)

-

\(\checkmark\)

\(\checkmark\)

-

86.81

80.57

94.42

86.23

4

\(\checkmark\)

\(\checkmark\)

\(\checkmark\)

\(\checkmark\)

-

89.11

82.37

94.31

87.62

5

\(\checkmark\)

\(\checkmark\)

\(\checkmark\)

-

\(\checkmark\)

87.24

80.04

94.13

87.19

6

\(\checkmark\)

\(\checkmark\)

\(\checkmark\)

\(\checkmark\)

\(\checkmark\)

90.12

83.06

94.52

88.07