Skip to main content

Table 2 Performances of the proposed method

From: Multi-tissue and multi-scale approach for nuclei segmentation in H&E stained images

Organ

Computational time (s)

Object-level performance

Pixel-level performance

Recall

Precision

F1-score

CS (%)

US (%)

SE (%)

Colon

22.89 ± 2.15

0.9505 ± 0.0121

0.9048 ± 0.0114

0.9270 ± 0.0086

86.78 ± 1.97

8.69 ± 2.00

4.53 ± 1.14

Liver

11.32 ± 1.25

0.9249 ± 0.0267

0.9547 ± 0.0114

0.9392 ± 0.0101

87.17 ± 4.55

5.81 ± 2.42

7.02 ± 2.37

Bone

13.10 ± 1.13

0.9486 ± 0.0290

0.9362 ± 0.0203

0.9417 ± 0.0077

74.15 ± 4.17

21.35 ± 4.30

4.07 ± 2.49

Prostate

12.28 ± 1.31

0.9533 ± 0.0127

0.9404 ± 0.0147

0.9467 ± 0.0106

77.47 ± 7.72

18.79 ± 7.31

3.74 ± 0.88

Adrenal gland

18.02 ± 1.26

0.9126 ± 0.0300

0.9239 ± 0.0312

0.9174 ± 0.0129

84.60 ± 4.44

7.33 ± 2.55

8.06 ± 2.62

Thyroid

23.71 ± 5.94

0.9335 ± 0.0296

0.8914 ± 0.0221

0.9112 ± 0.0038

81.62 ± 6.18

12.61 ± 5.39

5.77 ± 2.60

Overall

16.89 ± 5.72

0.9372 ± 0.0288

0.9253 ± 0.0293

0.9305 ± 0.0161

81.97 ± 7.05

12.43 ± 7.32

5.53 ± 2.66

  1. Data are reported as mean ± standard deviation