README.md

metadata

title: APEC Angiography Segmentation
emoji: 🫀
colorFrom: red
colorTo: pink
sdk: streamlit
sdk_version: 1.28.1
app_file: app.py
pinned: false

Apec Segmentation

Apec paper

Please see here for our paper in the International Journal of Cardiology

Please cite it!

Mahendiran, T., Thanou, D., Senouf, O., Jamaa, Y., Fournier, S., De Bruyne, B., ... & Andò, E. (2025). Apec Segmentation: An open-source, user-guided deep learning tool for coronary artery segmentation. International journal of cardiology, 418, 132598.

Apec in the news

Apec segmentation is being used in this RTS reportage on AI in Cardiology (in French)

Online Example

Please visit https://imaging.epfl.ch/angiopy-segmentation/ for a live demo of this code on some example DICOM images

Description

This software allows single arteries to be segmented given a few clicks on a single time frame with a PyTorch 2 Deep Learning model.

Installing and running

• Install dependencies: pip install -r requirements.txt
• Launch Streamlit Web Interface: streamlit run angioPySegmentation.py --server.fileWatcherType none

...a website should pop up in your browser!

You need to create a /Dicom folder and put some angiography DICOMs in there

How to run the project

Create virtual environment and activate it

uv venv
source .venv/bin/activate
uv pip install -r requirements.txt