EnteroidSeg is an example of image processing pipeline developed to identify nuclei and cell-types in the 2d enteroid cultures [1]. Example code for segmentation of nuclei, EdU+ nuclei, stem cells, and goblet cells are provided. This set of code accompanies a paper on 2d enteroid culture and analysis, which should be cited for this code [2].
The package was developed with Python.
The easiest way to set up the appropriate environment is through conda. Miniconda3 can be install ed https://docs.conda.io/en/latest/miniconda.html
After installing Miniconda, download the package and navigate to the EnteroidSeg folder. Setup the Python environment with the following command.
conda env create --file=environment.yaml
A conda environment named enteroidseg will be created. Activate the environment to run the scripts in this package. The environment can be activated with the following command
source activate enteroidseg
The required Python version and packages can also be installed manually. The required version and packages are listed in requirements.txt
Segmentation using the provided sample images (under images) can be done by running scripts for each segmentation type.
To run the nuclear segmentation, navigate to the enteroidseg folder and execute the following to command.
python nuclear_segmentation.py
The output the of the script consists of three files and will be store in output
- dna_segmentation.tiff: segmentation file with labeled segmented objects
- dna_overlay.png: visualization of segmentation result overlayed on the raw input image
- dna_pipeline_result.png: visualization of main steps in the pipeline
To run the EdU+ nuclei segmentation, navigate to the enteroidseg folder and execute the following to command.
python edu_segmentation.py
The output the of the script consists of three files and will be store in output
- edu_segmentation.tiff: segmentation file with labeled segmented objects
- edu_overlay.png: visualization of segmentation result overlayed on the raw input image
- edu_pipeline_result.png: visualization of main steps in the pipeline
To run the stem cell segmentation, navigate to the enteroidseg folder and execute the following to command.
python stem_segmentation.py
The output the of the script consists of three files and will be store in output
- stem_segmentation.tiff: segmentation file with labeled segmented objects
- stem_overlay.png: visualization of segmentation result overlayed on the raw input image
- stem_pipeline_result.png: visualization of main steps in the pipeline
To run the goblet cell segmentation, navigate to the enteroidseg folder and execute the following to command.
python goblet_segmentation.py
The output the of the script consists of three files and will be store in output
- goblet_segmentation.tiff: segmentation file with labeled segmented objects
- goblet_overlay.png: visualization of segmentation result overlayed on the raw input image
- goblet_pipeline_result.png: visualization of main steps in the pipeline
This project is licensed under the MIT License - see the LICENSE.md file for details
1: Thorne, C.A.*, Chen, I.W.*, Sanman, L.E., Cobb, M.H., Wu, L.F., and Altschuler, S.J. (2018). Enteroid Monolayers Reveal an Autonomous WNT and BMP Circuit Controlling Intestinal Epithelial Growth and Organization. Dev. Cell 44, 624–633.e4.
2: Sanman, L.E.*, Chen, I.W.*, Bieber, J.M., Thorne, C.A., Wu, L.F., and Altschuler, S.J. (2019). Generation and quantitative imaging of enteroid monolayers. Methods in Molecular Biology