linkinpy-segmentation 0.0.2

LinkinPy CLI package for deep-learning based bioimage segmentation

LinkinPy Segmentation

linkinpy-segmentation exposes deep-learning segmentation methods as LinkinPy-compatible command-line tools. The first method uses Cellpose cyto3 for general cell segmentation, following the mAIcrobe idea of first-use model download and cached inference, but without a napari GUI dependency.

Cellpose Segmentation

linkinpy-cellpose-segment input.tif output_labels.tif --model-type cyto3 --diameter 30

The command stores Cellpose models in:

~/.linkinpy/models/cellpose

On each run it checks whether the requested model files are already present. If they are missing, the command asks Cellpose to download them, then runs inference and writes the segmentation labels as a TIFF image.

LinkinPy Metadata

This package includes linkinpy.yaml, so linkinpy-parse can generate richer GUI metadata for ImageJ/Fiji and napari.

Development

uv sync
uv run pytest