Skip to main content

Table 2 Results of comparison experiments on bacteria segmentation task

From: DB-DCAFN: dual-branch deformable cross-attention fusion network for bacterial segmentation

Methods

Dice (mean ± SD, %)

Jaccard (mean ± SD, %)

Aba

Kpn

Pae

All

Aba

Kpn

Pae

All

U-Net

61.58 ± 14.85

59.26 ± 21.21

66.28 ± 18.08

62.35 ± 18.58

46.09 ± 15.04

45.14 ± 20.29

52.04 ± 18.45

47.76 ± 18.41

CE-Net

67.74 ± 14.86

59.48 ± 21.23

66.41 ± 13.87

64.41 ± 17.46

52.97 ± 15.66

45.35 ± 20.23

51.13 ± 13.71

49.69 ± 17.14

UCtransNet

62.75 ± 15.86

63.35 ± 16.41

68.96 ± 17.60

65.05 ± 16.89

47.58 ± 16.20

48.32 ± 16.44

55.00 ± 17.96

50.34 ± 17.22

Swin-Unet

67.41 ± 9.52

59.15 ± 21.40

69.19 ± 16.79

65.13 ± 17.40

51.57 ± 10.19

45.00 ± 19.92

55.26 ± 18.64

50.52 ± 17.51

TransUNet

70.64 ± 8.99

61.80 ± 20.80

68.43 ± 19.52

66.81 ± 17.86

55.35 ± 10.75

47.78 ± 20.45

54.97 ± 20.23

52.58 ± 18.24

Ours

70.57 ± 10.63

65.36 ± 20.62

70.49 ± 14.90

68.73 ± 16.26

55.54 ± 12.47

51.55 ± 19.78

56.40 ± 17.24

54.44 ± 17.03