Metadata-Version: 2.5
Name: napari-he-dapi
Version: 0.1.0
Summary: napari plugin: H&E <-> DAPI virtual staining (runs the he-dapi model in the viewer)
Project-URL: Homepage, https://github.com/urbiologicalpa/he-dapi-translator
Project-URL: Repository, https://github.com/urbiologicalpa/he-dapi-translator
Project-URL: Bug Tracker, https://github.com/urbiologicalpa/he-dapi-translator/issues
Author: urbiologicalpa
License: MIT
Keywords: dapi,he,histopathology,napari,napari-plugin,virtual-staining
Classifier: Framework :: napari
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Scientific/Engineering :: Image Processing
Requires-Python: >=3.10
Requires-Dist: he-dapi>=0.1.0
Requires-Dist: magicgui>=0.7
Requires-Dist: napari>=0.4.18
Requires-Dist: qtpy>=2.0
Description-Content-Type: text/markdown

# napari-he-dapi

A [napari](https://napari.org) plugin for **H&E ↔ DAPI virtual staining**, powered by
[`he-dapi`](https://pypi.org/project/he-dapi/).

Open an H&E image in napari, launch the widget from **Plugins → H&E <-> DAPI**,
pick the direction, and the predicted virtual stain appears as a new layer.

## Install
```bash
pip install napari-he-dapi
```

## Use
1. Open napari and load an H&E image (`File → Open`).
2. `Plugins → H&E <-> DAPI Virtual Staining → H&E <-> DAPI`.
3. Choose **direction** (`he2dapi`), click **Run virtual staining**.

Weights download automatically from
[`urbiologicalpa/he-dapi-translator`](https://huggingface.co/urbiologicalpa/he-dapi-translator).

## Status
`he2dapi` (paired Pix2Pix) available; `dapi2he` (CycleGAN) when unpaired training completes.

## License
MIT. Research demonstration only — not validated for clinical use.
