Table 8 Comparison of descriptive statistics from models trained with segments, segments with vessel (color channel) and segments with spleen on challenge cohort CCH.

From: Fully automated deep learning based auto-contouring of liver segments and spleen on contrast-enhanced CT images

 

Seg 1, N = 251

Seg 2, N = 251

Seg 3, N = 251

Seg 4, N = 251

Seg 5–8, N = 251

Spleen, N = 251

(IntraMD2a = 0.88)

N = 331

(IntraMD2a = 0.94)

(IntraMD2a = 0.92)

 (IntraMD2a = 0.99)

 

(InterMD2b = 0.82)

(InterMD2b = 0.85)

(InterMD2b = 0.91)

(InterMD2b = 0.88)

 (InterMD2b = 0.96)

 

MpaU-Net1

MnnUnet1

Mseg+spleen1

Mvess1

MpaU-Net1

MnnUnet1

Mseg+spleen1

Mvess1

MpaU-Net1

MnnUnet1

Mseg+spleen1

Mvess1

MpaU-Net1

MnnUnet1

Mseg+spleen1

Mvess1

MpaU-Net1

MnnUnet1

Mseg+spleen1

Mvess1

Mseg+spleen1

Dice

0.87

0.88

0.88

0.88

0.80

0.80

0.80

0.81

0.83

0.85

0.85

0.86

0.80

0.85

0.85

0.84

0.96

0.97

0.97

0.96

0.95

0.85,0.05

0.88,0.04

0.88,0.04

0.87,0.05

0.79, 0.05

0.80, 0.05

0.80, 0.05

0.81, 0.04

0.83, 0.06

0.85, 0.05

0.85, 0.05

0.85, 0.06

0.80, 0.07

0.85, 0.06

0.84, 0.06

0.84, 0.06

0.96, 0.01

0.97, 0.01

0.97, 0.01

0.96, 0.01

0.96, 0.01

0.94,0.72

0.97,0.77

0.96,0.76

0.97,0.77

0.88, 0.67

0.88, 0.65

0.89, 0.65

0.87, 0.68

0.92, 0.67

0.94, 0.67

0.95, 0.70

0.94, 0.65

0.93, 0.66

0.95, 0.74

0.95, 0.73

0.94, 0.72

0.99, 0.92

0.99, 0.95

0.99, 0.95

0.99, 0.94

0.99, 0.93

\({{\text{HD}}}_{95}^{3}\)

5

3.8

3.8

4.3

10

9.8

10.0

10.7

10

9.1

8.8

9.0

14

8.6

8.4

8.9

8

6.1

6.1

6.0

2.0

6, 3

4.1, 2.3

4.2, 2.6

4.4, 2.3

12, 5

11.5, 5.0

11.4, 5.1

12.0, 5.9

11, 4

9.3, 3.2

9.5, 3.2

9.5, 3.0

16, 9

10.5, 4.9

10.8, 5.2

10.5, 5.0

9, 6

7.3, 5.2

7.6, 5.7

7.3, 4.8

1.9, 0.5

15, 2

12.8, 0.7

14.1, 0.7

13.0, 0.7

25, 5

25.9, 5.6

25.2, 5.5

29.3, 5.6

24, 6

15.9, 4.9

16.0, 5.0

16.6, 4.6

43, 4

23.4, 3.1

24.0, 3.2

21.9, 3.4

26, 2

22.8, 1.4

23.2, 1.4

21.9, 1.0

2.8, 0.7

Avg.\({{\text{HD}}}_{{\text{A}}}^{3}\)

0.26

0.21

0.21

0.22

0.76

0.71

0.69

0.74

0.58

0.45

0.49

0.47

1.17

0.52

0.54

0.45

0.15

0.10

0.09

0.09

0.06

0.35, 0.30

0.25, 0.20

0.25,0.22

0.27,0.20

0.88, 0.53

0.81, 0.46

0.81, 0.47

0.83, 0.45

0.73, 0.52

0.56, 0.33

0.55, 0.27

0.58, 0.37

1.06, 0.64

0.63, 0.48

0.66, 0.51

0.64, 0.47

0.19, 0.14

0.11, 0.09

0.12, 0.11

0.11, 0.09

0.06, 0.02

1.42, 0.06

1.10, 0.02

1.21,0.03

1.08,0.02

2.19, 0.24

2.14, 0.30

2.28, 0.41

1.91, 0.36

1.99, 0.23

1.61, 0.13

1.30, 0.12

1.95,0.18

2.49, 0.12

2.07, 0.07

2.12, 0.07

1.86, 0.08

0.51, 0.01

0.43, 0.01

0.44, 0.01

0.40, 0.01

0.10, 0.00

PDV

14

8

8

11

18

16

18

18

13

9

8

8

9

7

8

6

2

2

3

3

4

17, 12

11, 8

11, 10

12, 8

19, 12

19, 13

19, 11

19, 11

14, 13

12, 9

12, 10

11, 10

11, 8

10, 7

10, 8

9, 8

2, 2

3, 2

3, 2

3, 2

4, 2

52, 1

31, 0

34, 0

31, 1

44, 1

49, 0

50, 2

47, 2

46, 0

37, 1

40, 0

37, 0

26, 0

30, 0

33, 0

30, 0

6, 0

7, 0

7, 0

8, 0

8, 0

Back to article page