Skip to main content

Napari plugin to manually correct epithelia segmentation in movies

Project description

EpiCure

License BSD-3 PyPI Python Version napari hub DOI



Napari plugin to ease manual correction of epithelia segmentation in movies.



To analyse individual cell trajectory from epithelia movies marked for cell-cell junctions, a very precise segmentation and tracking is required. Several tools such as TissuAnalyzer, Epyseg, CellPose or Dist2Net perform very good segmentation (~5% of errors). However, this still implies a high amount of cells to correct manually.

EpiCure allows to decrease the burden of this task. Several features are proposed to ease the manual correction of the segmented movies, such as error detection, numerous shortcuts for editing the segmentation, option for tracking, display and measure/export options. EpiCure detect segmentation errors by taking advantage of temporal information. When a correction is done at a given frame, EpiCure relink the track to adjust for the changes.

See the full documentation here

EpiCure interface

Installation

Install plugin

To install EpiCure on a fresh python virtual environment, type inside the environement:

pip install epicure

Then launch Napari, and the plugin should be visible in the Plugins list.

If you already have an environment with Napari installed, you can also install it directly in Napari>Plugins>Install/Uninstall plugins

Install code

To have the code to be able to modify it, clone this repository. You can use pip install -e . so that everytime you update the code, the plugin will be updated.

Dependencies

The input files of EpiCure can be already tracked or not. Tracking options are proposed in EpiCure:

  • Laptrack centroids
  • Laptrack overlaps

Usage

Refer to the documentation for documentation of the different steps possible in the pipeline.

References

If you use EpiCure, thank you for citing our work:

EpiCure is not published yet, you can cite it using Zenodo for now: https://doi.org/10.5281/zenodo.13952184

Contributing and Feedback

EpiCure is mainly developed in CNRS UMR3738, in the Developmental and Stem Cell Biology Department of Institut Pasteur. If you have a question on using EpiCure or ask to add a feature, either file an issue or write in the imagesc forum.

Any contribution is most welcome. Do not hesitate to contact us beforehand through filing an issue (choose "Other questions/comments" type). To suggest the addition of a new feature, you can also contact us by filing an issue choosing the "Feature request" option.

If you encounter a code related issue using EpiCure, please file an issue in this repository.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

epicure-1.5.3.tar.gz (2.1 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

epicure-1.5.3-py3-none-any.whl (137.5 kB view details)

Uploaded Python 3

File details

Details for the file epicure-1.5.3.tar.gz.

File metadata

  • Download URL: epicure-1.5.3.tar.gz
  • Upload date:
  • Size: 2.1 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.0.0 CPython/3.10.12

File hashes

Hashes for epicure-1.5.3.tar.gz
Algorithm Hash digest
SHA256 622241dcdf73ecc72abaddbde21454f8c95416356fea81e805dec59b41b45f9e
MD5 c2705444eb43314a33c9f9a943e25281
BLAKE2b-256 86a14dc52680e6e8ca75c245bdc096ee227ccc051cb3c14d2ba9c3ee890fe294

See more details on using hashes here.

File details

Details for the file epicure-1.5.3-py3-none-any.whl.

File metadata

  • Download URL: epicure-1.5.3-py3-none-any.whl
  • Upload date:
  • Size: 137.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.0.0 CPython/3.10.12

File hashes

Hashes for epicure-1.5.3-py3-none-any.whl
Algorithm Hash digest
SHA256 6bb0f177c0f712ae65c948b45a2760f156929ab0af773687dfedb4259e741b78
MD5 d821a048956e605443a8c6f5fad1004c
BLAKE2b-256 7fd492181626573aeac70701edb11b81324e1a738470f91e37a1418c64b5dc1a

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page