Skip to main content

Table 2 The whole liver region segmentation results in training cohort by separating the cases on which anatomical landmark data either had effect and no effect on the segmentation accuracy

From: An automated liver segmentation in liver iron concentration map using fuzzy c-means clustering combined with anatomical landmark data

The number of cases

Evaluation matrices

FCM

FCM combined with anatomical landmark data

Effect: 138 cases

%DSC

81.89 ± 18.75

93.55 ± 2.54

%JC

72.16 ± 18.30

87.99 ± 4.37

H (mm)

62.86 ± 27.34

24.79 ± 15.34

Non-effect: 303 cases

%DSC

93.20 ± 7.04

93.22 ± 5.75

%JC

87.92 ± 9.84

87.75 ± 8.38

H (mm)

29.83 ± 21.45

31.89 ± 21.84