napari-labelprop 0.0.1

Label propagation through deep registration

napari-labelprop

Label propagation through deep registration.

---

This napari plugin was generated with Cookiecutter using @napari's cookiecutter-napari-plugin template.

Installation

To install this project :

pip install napari['all']
git clone https://github.com/nathandecaux/napari-labelprop.git
cd napari-labelprop
pip install -e .

Usage

Open napari from terminal and start using functions from 'napari-labelprop' plugin (Under Plugins scrolling menu).

Available functions are :

• Inference : Propagate labels from trained weights (Pytorch checkpoint required)
• Training : Start training from scratch or from a pretrained model
• Remove annotated slices : (testing purpose) Function to remove every annotations except for declared slices. Kept slices must be declared in the 'slices' field using comma (',') separation (eg. 5,12,43)

PS : "pretraining" option in the Training menu is still under development

Alternatively, napari and plugin widgets can be called directly from python scripts :

import nibabel as ni
import napari

viewer = napari.view_image(ni.load('images.nii.gz').get_fdata())
viewer.add_labels(ni.load('segmentation.nii.gz').get_fdata().astype('uint8'))
dw, my_widget = viewer.window.add_plugin_dock_widget('napari-labelprop', 'Training')
my_widget.checkpoint_output_dir.value='~'
my_widget.checkpoint_name.value='checkpoint_name'
my_widget.z_axis.value=2
my_widget.pretraining.value=False
napari.run()

Contributing

Contributions are very welcome. Tests can be run with tox, please ensure the coverage at least stays the same before you submit a pull request.

License

Distributed under the terms of the BSD-3 license, "napari-labelprop" is free and open source software

Issues

If you encounter any problems, please [file an issue] along with a detailed description.