Skip to main content

Table 2 Comparison of our segmentation results with generally available segmentation methods

From: Automatic MRI segmentation of para-pharyngeal fat pads using interactive visual feature space analysis for classification

Masks

 

DICE

TPVF

FPVF

  

(%)

(%)

(%)

Our Algorithm

Avg.

77.9

79.1

24.1

 

Std.

4.1

6.8

10.5

Region Growing

Avg.

35.8

46.9

181.8

 

Std.

18.3

27.3

289.3

Fuzzy c-means

Avg.

43.4

52.3

92.1

 

Std.

13.3

20.3

78.4

MultiOtsu

Avg.

39.8

71.6

226.4

 

Std.

12.4

10.6

151.5

Watersheds

Avg.

28.6

19.8

10.8

 

Std.

23.7

18.3

14.1

Level Sets

Avg.

40.0

43.8

68.3

 

Std.

20.6

31.8

119.0