facebookresearch/fastMRI

A large-scale dataset of both raw MRI measurements and clinical MRI images.

Archived
51
/ 100
Established

Provides PyTorch data loaders, k-space subsampling functions, and evaluation metrics alongside baseline implementations (U-Net, VarNet) for accelerated MRI reconstruction from undersampled measurements. Supports both raw k-space data and reconstructed DICOM images across knee, brain, and prostate anatomies, with PyTorch Lightning modules for streamlined training pipelines. Includes reference implementations from published methods spanning reconstruction networks, artifact correction, and active acquisition strategies.

1,508 stars. No commits in the last 6 months.

Archived Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

1,508

Forks

418

Language

Python

License

MIT

Last pushed

Jan 21, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/facebookresearch/fastMRI"

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