Irregular cell shape segmentation using VollSeg

Workflow step:
Image SegmentationCell segmentation
Image SegmentationModel-based segmentation
Image modality:
Medical imaging

PyPI version napari hub License codecov Twitter Badge

This project provides the napari plugin for VollSeg, a deep learning based 2D and 3D segmentation tool for irregular shaped cells. VollSeg has originally been developed (see papers) for the segmentation of densely packed membrane labelled cells in challenging images with low signal-to-noise ratios. The plugin allows to apply pretrained and custom trained models from within napari. For detailed demo of the plugin see these videos and a short video about the parameter selection

Installation & Usage

Install the plugin with pip install vollseg-napari or from within napari via Plugins > Install/Uninstall Package(s)…. If you want GPU-accelerated prediction, please read the more detailed installation instructions for VollSeg.

You can activate the plugin in napari via Plugins > VollSeg: VollSeg. Example images for testing are provided via File > Open Sample > VollSeg.

If you use this plugin for your research, please cite us.


This package is compatible with Python 3.6 - 3.9.

  1. Please first install TensorFlow (TensorFlow 2) by following the official instructions. For GPU support, it is very important to install the specific versions of CUDA and cuDNN that are compatible with the respective version of TensorFlow. (If you need help and can use conda, take a look at this.)

  2. VollSeg can then be installed with pip:

    • If you installed TensorFlow 2 (version 2.x.x):

      pip install vollseg


VollSeg comes with different options to combine CARE based denoising with UNET, StarDist and segmentation in a region of interest (ROI). We present some examples which are represent optimal combination of these different modes for segmenting different cell types. We summarize this in the table below:

Example ImageDescriptionTraining DataTrained ModelGT imageOptimal combinationNotebook CodeModel PredictionMetrics
Light sheet fused from four angles 3D single channelTraining Data ~320 GBUNET modelUNET model, slice_merge = FalseColab Notebook
Confocal microscopy 3D single channel 8 bitTraining DataDenoising Model and StarDist ModelStarDist model + Denoising Model, dounet = FalseColab Notebook
LaserScanningConfocalMicroscopy 2D single channelDatasetUNET ModelUNET modelColab NotebookNo Metrics
TIRF + MultiKymograph Fiji tool 2D single channelTraining DatasetUNET ModelUNET modelColab NotebookNo Metrics
XRay of Lung 2D single channelTraining DatasetUNET ModelUNET modelColab Notebook
LaserScanningConfocalMicroscopy 2D single channellTest DatasetPrivateUNET modelColab NotebookNo metrics
LaserScanningConfocalMicroscopy 3D single channellTest DatasetPrivateUNET model + StarDist model + ROI modelColab Notebook

Troubleshooting & Support

  • The image.sc forum is the best place to start getting help and support. Make sure to use the tag vollseg, since we are monitoring all questions with this tag.
  • If you have technical questions or found a bug, feel free to open an issue.


  • 2.3.7

Last updated:

  • 03 October 2022

First released:

  • 10 December 2021


  • BSD-3-Clause

GitHub activity:

  • Stars: 11
  • Forks: 1
  • Issues + PRs: 0

Python versions supported:

Operating system:


  • vollseg
  • napari (>=0.4.13)
  • magicgui (>=0.4.0)
  • tensorflow ; platform_system != "Darwin" or platform_machine != "arm64"
  • tensorflow-macos ; platform_system == "Darwin" and platform_machine == "arm64"

Sign up to receive updates