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

Table 2 Mean ± std for ROI based metrics using default models for nuclear and cytoplasm segmentations

Method	Region	F1 Score	IoU score	False discovery rate	Fowlkes–Mallows index
Mesmer	Nucleus	0.91 ± 0.06	0.85 ± 0.09	0.08 ± 0.07	0.91 ± 0.06
CellPose	Nucleus	0.81 ± 0.16	0.71 ± 0.18	0.09 ± 0.11	0.82 ± 0.15
SplineDist	Nucleus	0.81 ± 0.09	0.69 ± 0.12	0.14 ± 0.09	0.81 ± 0.09
Columbus	Nucleus	0.64 ± 0.14	0.49 ± 0.14	0.21 ± 0.12	0.66 ± 0.13
AICS	Nucleus	0.47 ± 0.20	0.33 ± 0.19	0.30 ± 0.13	0.50 ± 0.18
UF-UNet	Nucleus	0.16 ± 0.20	0.11 ± 0.17	0.72 ± 0.21	0.18 ± 0.19
Mesmer	Cytoplasm	0.83 ± 0.09	0.72 ± 0.13	0.16 ± 0.10	0.83 ± 0.09
CellPose	Cytoplasm	0.32 ± 0.19	0.20 ± 0.14	0.29 ± 0.24	0.37 ± 0.19
SplineDist	Cytoplasm	N/A	N/A	N/A	N/A
Columbus	Cytoplasm	0.41 ± 0.15	0.27 ± 0.12	0.46 ± 0.15	0.42 ± 0.15
AICS	Cytoplasm	0.17 ± 0.13	0.10 ± 0.08	0.59 ± 0.21	0.20 ± 0.12
UF-UNet	Cytoplasm	N/A	N/A	N/A	N/A

ISSN: 1471-2105