The napari hub is transitioning to a community-run implementation due to launch in June 2025.
Since October 1, 2024, this version is no longer actively maintained and will not be updated. New plugins and plugin updates will continue to be listed.

Napari nucleAIzer plugin

napari-nucleaizer

A GUI interface for training and prediction using the nucleAIzer nuclei detection method.

License PyPI Python package codecov Documentation Status

GUI for the nucleaAIzer method in Napari.

Plugin interface in napari.

Overview

This is a napari plugin to execute the nucleaizer nuclei segmentation algorithm.

Main functionalities

Using this plugin will be able to

  1. Load your image into Napar, then outline the nuclei.
  2. Specify an image folder containing lots of images and an output folder, and automatically segment all of the images in the input folder.
  3. If you are not satisfied with the results, you can train your own model:
    1. You can use our pretrained models and fine tune them on your data.
    2. You can skip the nucleaizer pipeline and train only on your data.

Supported image types

We have several pretrained models for the following image modelities:

  • fluorescent microscopy images
  • IHC stained images
  • brightfield microscopy images,

among others. For the detailed descriptions of our models, see: https://zenodo.org/record/6800341.

How it works?

For the description of the algorithm, see our paper: "Hollandi et al.: nucleAIzer: A Parameter-free Deep Learning Framework for Nucleus Segmentation Using Image Style Transfer, Cell Systems, 2020. https://doi.org/10.1016/j.cels.2020.04.003"

The original code (https://github.com/spreka/biomagdsb) is partially transformed into a python package (nucleaizer_backend) to actually perform the operations. See the project page of the backend at: https://github.com/etasnadi/nucleaizer_backend.

If you wish to use the web interface, check: http://nucleaizer.org.

All functionalities.

Install

  1. Create an environment (recommended).

  2. Install napari: pip install "napari[pyqt5]". Other methods: https://napari.org/tutorials/fundamentals/installation.html

  3. Install the plugin into napari:

    • User mode from PyPI: start Napari (command line: napari) and select he Install/Uninstall Plugins... under the Plugins menu. In the popup, filter for napari-nucleaizer.

    • Developer mode: clone this project and use pythhon3 -m pip install -e <path> to install the project locally into the same evnrionment as napari. It has the advantage that you will have the latest version.

Run

  1. Start Napari by calling napari from the command line.
  2. Then, activate the plugin in the Plugins menu. If you successfully installed the plugin, you have to see something like this:

Plugin interface in napari.

Further help

See the documentation (work in progress).

Issues

Use the github issue tracker if you experinece unexpected behaviour.

Contact

You can contact me in e-mail where MY-INSTITUTE is brc.hu.

Version:

  • 0.2.5

Last updated:

  • 01 September 2023

First released:

  • 08 September 2021

License:

Supported data:

  • Information not submitted

Plugin type:

GitHub activity:

  • Stars: 1
  • Forks: 0
  • Issues + PRs: 0

Python versions supported:

Operating system:

Requirements:

  • napari
  • qtpy
  • jsonpickle
  • numpy
  • scikit-image
  • imageio
  • nucleaizer-backend