fidoptOtsu nuclei
A classical baseline with no learnt weights: Otsu's threshold with scikit-image: the nuclei above it on a stained section's haematoxylin (colour deconvolution), or on the side of it that holds fewer pixels on a grey image; small holes and specks removed.
SegmentationCPUversion scikit-image 0.26.0HISTOLOGY, MICROSCOPYBSD-3-Clause
Run it
With its KonfAI app, at the benchmark's settings (the fidopt app repositories are private for now: a Hugging Face token with access opens them):
pip install konfai-apps konfai-apps infer fideus-labs/fidopt-segmentation:Otsu_Nuclei -i image.nii.gz -o out
The app on Hugging Face: its model, its settings and how it is scored.
Where it works
Its place on each kind of problem it has results on, among the methods ranked there. A method that leads one problem can trail another: read the one closest to yours.
| Problem | Place | Ranked | Datasets |
|---|---|---|---|
| Cell nuclei on histology and fluorescence microscopy, 2D segmentation | 1 | of 1 | 2 of 2 |
Results
| Dataset | # | Read by | Score | Failed | Time s |
|---|---|---|---|---|---|
| Data Science Bowl 2018, nuclei of many experiments | 1 | Dice | 0.861 | 0 | 5 |
| NuInsSeg, nuclei outlined by hand on H&E | 1 | Dice | 0.636 | 0 | 5 |
- Reference
- Otsu, IEEE Trans. SMC 1979; Ruifrok and Johnston, Anal. Quant. Cytol. Histol. 2001; van der Walt et al., PeerJ 2014