StarDist ImageJ/Fiji Plugin

This is the ImageJ/Fiji plugin for StarDist, which can be used to apply already trained models to new images.
Note: The plugin (currently) only supports 2D image and time lapse data.

See the main repository for links to our publications and the full-featured Python package that can also be used to train new models.

Installation

The StarDist plugin can be installed in Fiji by selecting both update sites CSBDeep and StarDist.
Concretely, you can follow these steps:

1. Start Fiji (or download and install it from here first).
2. Select Help > Update... from the menu bar.
3. Click on the button Manage update sites.
4. Scroll down the list and tick the checkboxes for update sites CSBDeep and StarDist, then click the Close button.
   (If StarDist is missing, click Update URLs to refresh the list of update sites.)
5. Click on Apply changes to install the plugin.
6. Restart Fiji.

Usage

stardist-imagej/auto_process contains automations complete with dialog box GUIs and a helpful guide for c-fos cell counting. Special thanks to The Rinker Lab at MUSC for allowing me to develop some of the first iterations of this.

• STARDIST Automated Cell Counting Protocol.docx -- a helpful guide for c-fos cell counting when your entire image is to be cell counted.
• STARDIST Step0 - Split Color Channels.ijm -- quickly resolves issues with 3 channel (RGB) TIFFs and splits them into individual color channels.
• STARDIST Step1 - Preprocessing.ijm -- conveniently automates:
  • 8-bit conversion
  • Image Rescaling
  • Smoothing
  • Background Subtraction
  • Median Filtering
  • Contrast Enhancement
  • Sharpening
• STARDIST Step2 - STARDIST Model Processing.py -- (should be run from Fiji macro editor NOT python) this is a handy python script by Martin Weigert with minor modifcations in the current fork.
• STARDIST Step3 - Postprocessing.ijm -- automates postprocessing and cell counting steps then saves a dataset:
  • Thresholding
  • Converting to Mask
  • Watershedding
  • Analyze Particles (counting)

See the wiki page for more information.