ImprintLab/MedSegDiff

Using Diffusion Models to Segment/Reconstruct Organs from Medical Images [AAAI Most influential Paper]

43
/ 100
Emerging

Combines diffusion probabilistic models with transformer-based architectures (V2) to jointly perform segmentation and reconstruction, enabling probabilistic uncertainty estimation through ensemble sampling. Supports accelerated inference via DPM-Solver for 50x faster sampling (1000→20 steps) and offers multi-GPU distributed training. Provides modular dataloaders for ISIC skin lesions and BRATS brain tumors, with extensibility for custom medical imaging tasks.

1,350 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 9 / 25
Community 22 / 25

How are scores calculated?

Stars

1,350

Forks

196

Language

Python

License

MIT

Last pushed

Sep 10, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/ImprintLab/MedSegDiff"

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