• Algorithm for round cells identification in the brightfield microscopy images.

    CellStar. Segmentation & tracking.

  • Documentation

    Here you can find various information about the algorithm

     

    Introduction

    Automatic tracking of cells in time-lapse microscopy is required to investigate a multitude of biological questions. To limit manipulations during cell line preparation and phototoxicity during imaging, brightfield imaging is often considered. Since the segmentation and tracking of cells in brightfield images is considered to be a difficult and complex task, a number of software solutions have been already developed.

     

    CellStar is one of such algorithms. It is optimized to segment and track images of budding yeast cells growing in monolayer (e.g. images from microfluidic chambers), however the algorithm can be also used to track other round objects (in brightfield as well as fluorescent images).

    Available implementations

    CellStar is provided in two independent implementations:

    • Matlab plugin - it is a version optimized for manual curation of  segmentation and tracking datasets. It contains GUI allowing to easily correct results of automatic tracking and segmentation. We recommend to use this implementation when you need very low error rates (e.g. in problems related to cell lineage analysis). To use this plugin you will need commercially available program Matlab together with image analysis and optionally optimization toolkits. 
    • CellProfiler plugin - it is a version seamlessly integrated with CellProfiler, free open-source software designed to enable biologists without training in computer vision or programming to quantitatively measure phenotypes from thousands of images automatically. This version does not allow for manual correction of segmentation / trajectories. On the other hand, it does not require any commercial software and comes with all analytic power of CellProfiler. We recommend to use this implementation if you would like to stay in the ecosystem of CellProfiler.

     

     

     

    Available manuals / knowledge

    Here you can find available documentation on how to use the plugins.

    Matlab plugin userguide

    Here you can download an official user guide for Matlab plugin. It covers various aspects of CellStar algorithm use like e.g. segmentation, tracking, parameter optimization, GUI usage.

    CellProfiler plugin user guide

    Here you can download an official user guide for CellProfiler plugin. It covers various aspects of CellStar algorithm usage within CellProfiler

    Comparision of various algorithms using YIT

    Before developing CellStar algorithm we spend some time in comparing existing solutions dedicated to segmentation and tracking budding yeast cells in brightfield images. It gave a rise to Yeast Image Toolkit (YIT) project. Please check out the YIT webpage for more information.

  • Media

    Take a look and enjoy!

    Segmentation of a single frame

    Illustration of brightfield to segmented image conversion with CellStar.

    Segmentation and tracking of time-lapse movie

    CellStar algorithm. The original images are displayed on the right, segmentation and tracking is overlaid on the images on the left.

  • Download

    Here you can find implementations of the algorithm

    MATLAB

    Stable version 1.0.1 is available to download here. The development version will soon be available on GITHUB.

     

    Plugin is compatible with MATLAB 2012a to 2014b.

    CellProfiler plugin

    Stable version 1.2.3 is available to download here. Source code can be find on GITHUB (sstoma/CellProfiler/yit).

     

    Plugin is compatible with CellProfiler 2.2 (use links here to download appropriate version: Windows, Linux, OS X). The package includes not only CellStar plugin but also examples of its usage to guide users on how to achieve best segmentation on a given type of imagery.

    Python package

    Stable version 1.3.0 will soon be available as a Python package. Source code can be find on GITHUB (CellProfiler/cellstar).

  • How to acknowledge our work?

    If you use our work, please use one of these citation in your manuscript to support us

    Matlab plugin

    If you used GUI and Matlab implementation

    Versari, Stoma & Batmanov et al., appeared in Journal of a Royal Society Interface.

    CellProfiler plugin

    If you used CellProfiler implementation

    Mroz&Kaczmarek et al., in preparation

  • Organizations

    These organizations and people supported our development

    University of Lile

    Lile, France

    Cristian VERSARI, Kiril BATMANOV, Cedric LHOUSSAINE

    ETH

    Zurich, Switzerland

    Szymon STOMA, Simon NOERRELYKKE, Gabor CSUCS

    INRIA

    Paris, France

    Gregory BATT

    CNRS

    Paris, France

    Pascal HERSEN, Artemis LLAMOSI, Matt DEYELL

    University of Wroclaw

    Wroclaw, Poland

    Filip MROZ, Adam KACZMAREK, Pawel RYCHLIKOWSKI

    Broad Institute

    Boston, USA

    Anne CARPENTER, Lee KAMENTSKY, Mark BRAY

  • Contact

    Please choose your contact person

    INRIA / CNRS, France

    Gregory Batt / Pascal Hersen 

    Please contact for the details of imaging expertise, biological datasets and microfluidics rutines.

    Computer Science Laboratory of Lille, France

    Cristian Versari

    Please contact for the details of algorithm and Matlab GUI specific questions.

    Image & Data Analysis Unit of Scientific Center for Optical and Electron Microscopy of ETH, Switzerland

    Szymon Stoma

    Please contact for the details of CellProfiler implementation and integration with pipelines / tools.