Skip to main content

Cellpose

Cellpose is a deep learning model for cell segmentation. It detects and outlines individual cells in microscopy images, supporting multiple cell types and automatic diameter estimation.

Input formats

.png, .jpg, .jpeg, .tiff, .bmp, .webp

Model variants

VariantDescription
cyto3 (default)Latest cytoplasm model — best general-purpose accuracy
cyto2Second-generation cytoplasm model
cytoOriginal cytoplasm model
nucleiNuclei-only detection

Parameters

ParameterRangeDefaultDescription
Model typecyto/cyto2/cyto3/nucleicyto3Which Cellpose model to use
Diameter0–500 px0 (auto)Expected cell diameter. Set to 0 for auto-detection.
Flow threshold0–10.4Maximum flow error per mask (advanced)
Cell probability threshold-6 to +60.0Cell probability cutoff (advanced)
Channels[int, int][0, 0]Cytoplasm and nucleus channel indices (advanced)

Outputs

OutputFormatDescription
Segmentation maskPNGCombined instance segmentation mask
PolygonsJSON (GeoJSON)Vector outlines of each detected cell

Presets

PresetDescription
Cell Segmentationcyto3 model with auto-diameter
Nuclei Onlynuclei model for nuclear detection

Compute requirements

ResourceRequirement
GPURequired — min 8 GB VRAM, 16 GB recommended
Duration~30 seconds per image