PanSeg

Warning

PanSeg was recently renamed from PlantSeg to highlight its capabilities beyond plant segmentation. Currently there are some technical issues regarding the installer on windows and the update procedure. If you encounter issues, please continue using version 2.0.0rc14 until the issues are resolved.

PanSeg is a tool for cell instance aware segmentation in densely packed 3D volumetric images. The pipeline uses a two stages segmentation strategy (Neural Network + Segmentation). The pipeline is tuned for plant cell tissue acquired with confocal and light sheet microscopy. Pre-trained models are provided.

Table of Contents

• Getting Started
• Installation
• Repository Index
• Citation

Getting Started

Checkout the documentation 📖 for more details.

full_workflow_20fps.mp4

Installation

The easiest way to get PanSeg is using the installer. Download it here

The installer comes with python and conda. Please go to the documentation for more detailed instructions.

For development, we recommend to clone the repo and install using:

conda env create -f environment-dev.yaml

The above command will create new conda environment panseg-dev together with all required dependencies.

Repository Index

The PanSeg repository is organised as follows:

• panseg: Contains the source code of PanSeg.
• docs: Contains the documentation of PanSeg.
• examples: Contains the files required to test PanSeg.
• tests: Contains automated tests that ensures the PanSeg functionality are not compromised during an update.
• evaluation: Contains all script required to reproduce the quantitative evaluation in Wolny et al..
• conda-reicpe: Contains all necessary code and configuration to create the anaconda package.
• constructor: Contains scripts for the installer creation.
• Menu: Contains scripts for OS Menu entries

PanSeg & PlantSeg

This project stated 2020 as PlantSeg, but its capabilities are not restricted to plant cells! To better reflect that, for the 2.0 release we changed the name to PanSeg, referring to plant and animal cells.

Citation

PanSeg 2.0

A new publication highlighting all the new features is currently on its way.
Until then, if you find our work useful, please cite the PlantSeg 1.0 paper below.

Plantseg 1.0

@article{wolny2020accurate,
  title={Accurate and versatile 3D segmentation of plant tissues at cellular resolution},
  author={Wolny, Adrian and Cerrone, Lorenzo and Vijayan, Athul and Tofanelli, Rachele and Barro, Amaya Vilches and Louveaux, Marion and Wenzl, Christian and Strauss, S{\"o}ren and Wilson-S{\'a}nchez, David and Lymbouridou, Rena and others},
  journal={Elife},
  volume={9},
  pages={e57613},
  year={2020},
  publisher={eLife Sciences Publications Limited}
}