Track analysis using TrackMate xml and csv generated tracks using NapaTrackMater as the base library

This GUI plugin allows you to do track analysis by using autoencoder models that convert the segmentation labels to point cloud representations. It takes a TrackMate generated XML and csv files and creates a master XML file by computing additional shape and dynamic features based on the generated point clouds.

Elaborate documentation for users of this repository at this website documentation

This plugin is intended to be used on 3D+time tracking data for researchers interested in performing cell-fate analysis for which the shape and dynamic features of cells in a track are relevant.

You will need to have a segmentation image in 3D generated by VollSeg or other such plugins along with tracking XML, spots, edges and tracks csv file generated from the Fiji plugin TrackMate. You can either use our autoencoder models to apply on your segmentation image to generate point cloud representations or upload your torch trained model based on our Lightning based package Lightning version.

If you find a bug with affinder, or would like support with using it, please raise an issue on the GitHub repository.

Please use the following citations if you use this in your work: https://conference.scipy.org/proceedings/scipy2021/varun_kapoor.html


  • 2.5.9

Last updated:

  • 01 May 2024

First released:

  • 31 December 2022


Supported data:

  • Information not submitted

Plugin type:

GitHub activity:

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

Python versions supported:

Operating system:


  • napari-plugin-engine>=0.1.4
  • caped-ai