HReynaud/EchoDiffusion

MICCAI 2023 code for the paper: Feature-Conditioned Cascaded Video Diffusion Models for Precise Echocardiogram Synthesis. EchoDiffusion is a collection of video diffusion models trained from scratch on the EchoNet-Dynamic dataset with the imagen-pytorch repo.

36
/ 100
Emerging

This project helps medical researchers and AI developers create realistic, synthetic echocardiogram videos. You provide a real echocardiogram video and specify a desired ejection fraction, and it generates new videos showing how that heart might look with the requested ejection fraction. This tool is for researchers developing and testing new diagnostic algorithms for heart conditions.

No commits in the last 6 months.

Use this if you need to generate high-quality, anatomically plausible synthetic echocardiogram videos with specific clinical parameters for research or algorithm development.

Not ideal if you are a clinician looking for a diagnostic tool for patient care, as this is a research tool for generating synthetic data.

echocardiography medical-imaging cardiology-research synthetic-data medical-AI-development
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

74

Forks

7

Language

Python

License

MIT

Last pushed

Oct 29, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/HReynaud/EchoDiffusion"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.