Skip to content

Latest commit

 

History

History
38 lines (28 loc) · 1.72 KB

README.md

File metadata and controls

38 lines (28 loc) · 1.72 KB

Logo

This repository contains a collection of scripts for the segmentation, registration and quantification of pairs of tumor tissue sections. Some of the functionality is available as both Python and ImageJ macro script:

Requirements:

  • H&E Segmentation: Python (Framework: Pytorch)
  • IF Segmentation: Python (Framework: scikit learn /Ilastik
  • Registration: Elastix, can be callled from Python or ImageJ macro
  • Measurement: Available in Python and ImageJ macro

Installation

Python:

Download and install Anaconda3. Create a new environment and install pytorch:

conda create -n microquant Python=3.8 git
conda activate microquant

Install pytorch according to the configuration on the Pytorch homepage. For instance, for Windows OS and CUDA 11.3 driver this can be achieved by

conda install pytorch torchvision torchaudio cudatoolkit=11.3 -c pytorch

You can now proceed to install microquant by cloning the repository and installing it:

git clone https://github.com/jo-mueller/MicroQuant.git
cd microquant
pip install -e .

ImageJ macro:

As for the imageJ macro scripts, it is sufficient to download Fiji and open the macro in the Fiji toolbar.

How to run

The source code for the Python scripts is provided here. We proide the ImageJ macro implementation as well as Python demo notebooks.