Lausanne University Hospital / EPFL (Ando, Thanou Labs)
Open-source, user-guided deep learning tool for coronary artery segmentation from invasive coronary angiography (ICA), designed to improve on traditional quantitative coronary angiography (QCA) edge-detection algorithms that typically require manual correction. Rather than segmenting the whole coronary tree indiscriminately, AngioPy lets the user click a handful of ground-truth points along a specific target vessel (including side branches), and predicts a binary mask for that single artery at the chosen cardiac-cycle time-step. Evaluated against an established QCA system on angiograms from the FAME 2 trial, AngioPy achieved an average F1 score of 0.927 (internal) and 0.924 (external validation), with vessel-diameter and lesion minimal-lumen-diameter measurements showing excellent agreement with QCA (r=0.93-0.96).
Architecture
Hybrid
User-guided (click-prompted) deep segmentation network: takes a single greyscale angiography frame plus a small number of user-clicked ground-truth pixels along the target vessel, and outputs a binary mask for that single artery
Framework
PyTorch
Added to catalog
2026-08-13
GPL 3.0
License for model weights only. Associated code may be licensed seperately, check code source for specific terms.
FAME 2 Trial Invasive Coronary Angiography Dataset (AngioPy)
User-guided binary segmentation mask of a single selected coronary artery from an invasive angiography frame