Skip to main content

Table 4 Mean ± std for feature-based metrics using default models for nuclear and cytoplasm segmentations

From: Unbiased image segmentation assessment toolkit for quantitative differentiation of state-of-the-art algorithms and pipelines

Method

Region

Intersection area

Intersection perimeter

Intersection mean intensity

Intersection solidity

Mesmer

Nucleus

0.89 ± 0.06

0.85 ± 0.08

0.89 ± 0.05

0.62 ± 0.20

CellPose

Nucleus

0.83 ± 0.09

0.77 ± 0.11

0.78 ± 0.12

0.53 ± 0.22

SplineDist

Nucleus

0.82 ± 0.07

0.77 ± 0.10

0.82 ± 0.08

0.30 ± 0.20

Columbus

Nucleus

0.76 ± 0.09

0.67 ± 0.11

0.78 ± 0.12

0.32 ± 0.15

AICS

Nucleus

0.69 ± 0.12

0.62 ± 0.13

0.73 ± 0.11

0.48 ± 0.16

UF-UNet

Nucleus

0.37 ± 0.22

0.32 ± 0.20

0.52 ± 0.16

0.24 ± 0.17

Mesmer

Cytoplasm

0.85 ± 0.78

0.84 ± 0.08

0.89 ± 0.07

0.58 ± 0.22

CellPose

Cytoplasm

0.66 ± 0.14

0.67 ± 0.14

0.67 ± 0.16

0.32 ± 0.20

SplineDist

Cytoplasm

N/A

N/A

N/A

N/A

Columbus

Cytoplasm

0.66 ± 0.15

0.61 ± 0.15

0.78 ± 0.12

0.36 ± 0.18

AICS

Cytoplasm

0.49 ± 0.14

0.44 ± 0.52

0.59 ± 0.16

0.33 ± 0.12

UF-UNet

Cytoplasm

N/A

N/A

N/A

N/A

  1. Bold indicates the top performer for a given region type for each metric shown