icon-lab/FedGAT
Official implementation of FedGAT: Generative Autoregressive Transformers for Model-Agnostic Federated MRI Reconstruction (https://arxiv.org/abs/2502.04521)
This project helps medical imaging centers and researchers improve the quality of MRI scans and collaborate more effectively, especially when data privacy is a concern. It takes raw MRI data from multiple sites and reconstructs high-quality images. It's designed for medical physicists, radiologists, and research institutions dealing with medical image analysis and federated learning.
No commits in the last 6 months.
Use this if you need to reconstruct high-quality MRI images from different medical centers without sharing the raw patient data directly, even if those centers use different imaging models.
Not ideal if you are working with a single MRI dataset or if data sharing between sites is not restricted, as simpler reconstruction methods might suffice.
Stars
20
Forks
1
Language
Python
License
MIT
Category
Last pushed
May 22, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/icon-lab/FedGAT"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
voxelmorph/voxelmorph
Unsupervised Learning for Image Registration
uncbiag/uniGradICON
uniGradICON: A Foundation Model for Medical Image Registration (MICCAI 2024)
junyuchen245/TransMorph_Transformer_for_Medical_Image_Registration
TransMorph: Transformer for Unsupervised Medical Image Registration (PyTorch)
DeepRegNet/DeepReg
Medical image registration using deep learning
MLI-lab/DeepDeWedge
Self-supervised deep learning for denoising and missing wedge reconstruction of cryo-ET tomograms