Skip to main content

Table 1 The Dice coefficient (DC) and Hausdorff distance (HD) (mean ± SD) for evaluating the accuracy of automatic brain segmentation quantitatively

From: Regional SUV quantification in hybrid PET/MR, a comparison of two atlas-based automatic brain segmentation methods

  

1CAU_L

2CAU_R

3PUT_L

4PUT_R

DC

Methods

Traditional

0.48 ± 0.13

0.51 ± 0.06

0.62 ± 0.09

0.49 ± 0.12

RATSI

0.64 ± 0.06

0.70 ± 0.05

0.75 ± 0.05

0.69 ± 0.05

P< 0.001

DH (pixels)

Methods

Traditional

11.80 ± 0.74

12.42 ± 1.19

11.03 ± 0.88

12.73 ± 1.87

RATSI

9.61 ± 0.75

9.56 ± 0.69

8.89 ± 0.68

9.39 ± 0.75

P< 0.001

  1. 1CAU_L: left caudate nucleus
  2. 2CAU_R: right caudate nucleus
  3. 3PUT_L: left putamen
  4. 4PUT_R: right putamen