https://github.com/lambda-science/myoquant

MyoQuant🔬: a tool to automatically quantify pathological features in muscle fiber histology images. Demo version deployed at: https://lbgi.fr/MyoQuant
https://github.com/lambda-science/myoquant

computer-vision deep-learning disease histology image medecine python pytorch quantification tensorflow

Last synced: 14 days ago
JSON representation

MyoQuant🔬: a tool to automatically quantify pathological features in muscle fiber histology images. Demo version deployed at: https://lbgi.fr/MyoQuant

• Host: GitHub
• URL: https://github.com/lambda-science/myoquant
• Owner: lambda-science
• License: agpl-3.0
• Created: 2022-10-26T12:45:01.000Z (almost 3 years ago)
• Default Branch: main
• Last Pushed: 2024-04-24T07:32:32.000Z (over 1 year ago)
• Last Synced: 2025-01-09T23:46:27.935Z (9 months ago)
• Topics: computer-vision, deep-learning, disease, histology, image, medecine, python, pytorch, quantification, tensorflow
• Language: Python
• Homepage: https://lbgi.fr/MyoQuant/
• Size: 3.75 MB
• Stars: 3
• Watchers: 2
• Forks: 1
• Open Issues: 6
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
![Twitter Follow](https://img.shields.io/twitter/follow/corentinm_py?style=social) ![PyPi](https://img.shields.io/badge/PyPi-https%3A%2F%2Fpypi.org%2Fproject%2Fmyoquant%2F-blueviolet) ![Pypi verison](https://img.shields.io/pypi/v/myoquant) ![PyPi Python Version](https://img.shields.io/pypi/pyversions/myoquant) ![PyPi Format](https://img.shields.io/pypi/format/myoquant) ![GitHub last commit](https://img.shields.io/github/last-commit/lambda-science/MyoQuant) ![GitHub](https://img.shields.io/github/license/lambda-science/MyoQuant)

# MyoQuant🔬: a tool to automatically quantify pathological features in muscle fiber histology images



  





  



MyoQuant🔬 is a command-line tool to automatically quantify pathological features in muscle fiber histology images.  

It is built using CellPose, Stardist, custom neural-network models and image analysis techniques to automatically analyze myopathy histology images.  

Currently MyoQuant is capable of quantifying centralization of nuclei in muscle fiber with HE staining, anomaly in the mitochondria distribution in muscle fibers with SDH staining and the number of type 1 muscle fiber vs type 2 muscle fiber with ATP staining.

An online demo with a web interface is available at [https://huggingface.co/spaces/corentinm7/MyoQuant](https://huggingface.co/spaces/corentinm7/MyoQuant). This project is free and open-source under the AGPL license, feel free to fork and contribute to the development.

#### _Warning: This tool is still in early phases and active development._

## How to install

### Installing from PyPi (Preferred)

**MyoQuant package is officially available on PyPi (pip) repository. [https://pypi.org/project/myoquant/](https://pypi.org/project/myoquant/) ![Pypi verison](https://img.shields.io/pypi/v/myoquant)**

Using pip, you can simply install MyoQuant in a python environment with a simple: `pip install myoquant`

### Installing from sources (Developers)

I recommend using UV for python environment management. See [UV documentation](https://github.com/astral-sh/uv/).

1. Clone this repository using `git clone https://github.com/lambda-science/MyoQuant.git`

2. Create a virtual environment by using `uv sync`

3. Run Myoquant with `uv run myoquant --help`

## Run Local Demo Instance

You can run the local streamlit private demo instance by running the following command:

`uv run streamlit run src/myoquant/streamlit/run.py`

And access: [ http://localhost:8501](http://localhost:8501)

## How to Use

#### **🆕 NEW:** MyoQuant now comes with a Text User Interface (TUI) for an easier discoverability of the different CLI parameter. **For this you can run `myoquant tui` or `uv run myoquant tui` to launch the TUI.**

![img.png](static/tui.png)

To use the command-line tool, first activate your venv in which MyoQuant is installed: `source .venv/bin/activate` or simply install the package using UV.  

Then you can perform SDH or HE analysis. You can use the command `myoquant --help` or `uv run myoquant --help` to list available commands.

## 💡Full command documentation is available here: [CLI Documentation](https://github.com/lambda-science/MyoQuant/blob/main/CLI_Documentation.md)

- **For SDH Image Analysis** the command is:  

  `myoquant sdh-analysis IMAGE_PATH`  

  Don't forget to run `myoquant sdh-analysis --help` for information about options.

- **For HE Image Analysis** the command is:  

  `myoquant he-analysis IMAGE_PATH`  

  Don't forget to run `myoquant he-analysis --help` for information about options.

- **For ATP Image Analysis** the command is:  

  `myoquant atp-analysis IMAGE_PATH`  

  Don't forget to run `myoquant atp-analysis --help` for information about options.

_If you're running into an issue such as `myoquant: command not found` please check if you activated your virtual environment with the package installed. And also you can try to run it with the full command: `python -m myoquant sdh-analysis --help` or `uv run myoquant sdh-analysis --help`

## Contact

Creator and Maintainer: [**Corentin Meyer**, PhD in Biomedical AI](https://cmeyer.fr) 

## Citing MyoQuant🔬

[placeholder]

## Examples

For HE Staining analysis, you can download this sample image: [HERE](https://www.lbgi.fr/~meyer/SDH_models/sample_he.jpg)  

For SDH Staining analysis, you can download this sample image: [HERE](https://www.lbgi.fr/~meyer/SDH_models/sample_sdh.jpg)  

For ATP Staining analysis, you can download this sample image: [HERE](https://www.lbgi.fr/~meyer/SDH_models/sample_atp.jpg)

1. Example of successful SDH analysis output with: `myoquant sdh-analysis sample_sdh.jpg`

![img.png](static/sdh_cli.png)

![image](https://i.imgur.com/4Nlnwdx.png)

2. Example of HE analysis: `myoquant he-analysis sample_he.jpg`

![image](https://i.imgur.com/q2cXgIf.png)

3. Example of ATP analysis with: `myoquan atp-analysis sample_atp.jpg`

![image](https://i.imgur.com/2ceiOx8.png)

## Advanced information

### HuggingFace🤗 repositories for Data and Model

In a effort to push for open-science, MyoQuant [SDH dataset](https://huggingface.co/datasets/corentinm7/MyoQuant-SDH-Data) and [model](https://huggingface.co/corentinm7/MyoQuant-SDH-Model) and availiable on HuggingFace🤗

## Partners



  



MyoQuant is born within the collaboration between the [CSTB Team @ ICube](https://cstb.icube.unistra.fr/en/index.php/Home) led by Julie D. Thompson, the [Morphological Unit of the Institute of Myology of Paris](https://www.institut-myologie.org/en/recherche-2/neuromuscular-investigation-center/morphological-unit/) led by Teresinha Evangelista, the [imagery platform MyoImage of Center of Research in Myology](https://recherche-myologie.fr/technologies/myoimage/) led by Bruno Cadot, [the photonic microscopy platform of the IGMBC](https://www.igbmc.fr/en/plateformes-technologiques/photonic-microscopy) led by Bertrand Vernay and the [Pathophysiology of neuromuscular diseases team @ IGBMC](https://www.igbmc.fr/en/igbmc/a-propos-de-ligbmc/directory/jocelyn-laporte) led by Jocelyn Laporte