napari-bootstrapper 0.2.0

A plugin to quickly generate dense ground truth with sparse labels

napari-bootstrapper

• Introduction
• Installation
• Getting Started
• Citation
• Issues
• Funding

Introduction

napari-bootstrapper is a tool to quickly generate dense 3D labels using sparse 2D labels within napari.

Dense 3D segmentations are generated using the 2D->3D method described in the preprint titled Sparse Annotation is Sufficient for Bootstrapping Dense Segmentation. In the preprint, we show sparse 2D annotations made in ~10 minutes on a single section can generate dense 3D segmentations that are reasonably good starting points for refining or bootstrapping.

This plugin is limited to the 2D->3D method and is intended for small volumes that can fit in memory. For more complex bootstrapping workflows, dedicated 3D models, and block-wise processing of large volumes, we recommend using the Bootstrapper CLI tool.

Installation

We recommend installing napari-bootstrapper via conda and pip:

1. Create a new environment called napari-bootstrapper:

conda create -n napari-bootstrapper -c conda-forge python==3.11 napari pyqt

2. Activate the newly-created environment:

conda activate napari-bootstrapper

3. You can install napari-bootstrapper via pip:

pip install napari-bootstrapper

• Or you can install the latest development version from github:

pip install git+https://github.com/ucsdmanorlab/napari-bootstrapper.git

Getting Started

Run the following in your terminal:

conda activate napari-bootstrapper
napari

Citation

If you find Bootstrapper useful in your research, please consider citing our preprint:

@article {Thiyagarajan2024.06.14.599135,
	author = {Thiyagarajan, Vijay Venu and Sheridan, Arlo and Harris, Kristen M. and Manor, Uri},
	title = {Sparse Annotation is Sufficient for Bootstrapping Dense Segmentation},
	year = {2024},
	doi = {10.1101/2024.06.14.599135},
	URL = {https://www.biorxiv.org/content/10.1101/2024.06.14.599135v2},
}

Issues

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

Funding

Chan-Zuckerberg Imaging Scientist Award DOI https://doi.org/10.37921/694870itnyzk from the Chan Zuckerberg Initiative DAF, an advised fund of Silicon Valley Community Foundation (funder DOI 10.13039/100014989).

NSF NeuroNex Technology Hub Award (1707356), NSF NeuroNex2 Award (2014862)