Downloads ยท 30 days
0
NKI-AI/direct-uniform
direct-uniform is a image-to-image model from NKI-AI. Use it when you need one image transformed into another. It is set up for direct. The card lists the license as apache-2.0.
UNIFORM (MIDL 2025) is a unified deep learning framework for reconstructing undersampled multi-coil MRI across diverse anatomical sites and contrasts, built on vSHARP inside the DIRECT toolkit.
Downloads ยท 30 days
0
Access
Public
Updated Aug 26, 2026
Repo size
410 MB
Likes
0
Public
Click a slice to open those files.
.pt404 MB ยท 99%
From the Hugging Face model README
UNIFORM (MIDL 2025) is a unified deep learning framework for reconstructing undersampled multi-coil MRI across diverse anatomical sites and contrasts, built on vSHARP inside the DIRECT toolkit.
๐ Paper: UNIFORM: A Unified Deep Learning Framework for Multi-organ and Multi-contrast MRI Reconstruction ยท PDF
๐๏ธ Method: vSHARP (MRI, 2025) ยท arXiv:2309.09954
๐ป Code: projects/UNIFORM

Figure 1 (MIDL 2025): one vSHARP model trained on fastMRI brain / knee / prostate and CMRxRecon cardiac data; evaluated at 2ร, 4ร, 6ร, and 8ร acceleration; zero-shot SSL on breast in the paper.
| File | Role |
|---|---|
uniform_vsharp.pt | Pretrained weights โ use with the YAMLs below |
uniform_brain.yaml | Brain inference (default 4ร FastMRIRandom, ACS 0.08) |
uniform_knee.yaml | Knee inference (default 4ร FastMRIEquispaced, ACS 0.08) |
uniform_prostate.yaml | Prostate inference (default 4ร FastMRIEquispaced, ACS 0.08) |
uniform_cardiac.yaml | Cardiac / CMRxRecon inference (default 4ร FastMRIEquispaced, ACS 0.08) |
git clone https://github.com/NKI-AI/direct.git
cd direct
conda create --name direct python=3.12
conda activate direct
pip install meson-python meson ninja
pip install --no-build-isolation -e ".[dev]"
pip install huggingface_hub
hf download NKI-AI/direct-uniform --local-dir ./uniform
direct predict ./predictions/brain \
--cfg ./uniform/uniform_brain.yaml \
--checkpoint ./uniform/uniform_vsharp.pt \
--data-root /path/to/fastmri/brain/multicoil_val \
--filenames-filter projects/UNIFORM/lists/test/brain_4x.lst \
--num-gpus 1
The first argument to direct predict is the prediction output directory.
Pass basenames via --filenames-filter (path to a .lst file under --data-root);
unlike training/validation, inference does not read filenames_lists from the YAML.
Edit inference.dataset.transforms.masking and uncomment one pair โ keep both lists
length 1 (DIRECT samples randomly from lists; multi-(R) lists are for training only):
masking:
name: FastMRIEquispaced # brain YAML defaults to FastMRIRandom
# accelerations: [8]
# center_fractions: [0.04]
accelerations: [4]
center_fractions: [0.08]
| Target (R) | accelerations | center_fractions |
|---|---|---|
| 2ร | [2] | [0.1] |
| 4ร | [4] | [0.08] |
| 6ร | [6] | [0.06] |
| 8ร | [8] | [0.04] |
| Anatomy | Source | Contrasts (paper) |
|---|---|---|
| Brain | fastMRI multi-coil | T1w, T2w, FLAIR |
| Knee | fastMRI multi-coil | PD with & without fat suppression |
| Prostate | fastMRI prostate | T2w |
| Cardiac | CMRxRecon 2023 | Cine, T1w, T2w (use ValidationSet/FullSample; flatten to P0XX_cine_*.mat) |
If you use this model, please cite UNIFORM, vSHARP, and the DIRECT toolkit.
@inproceedings{Yiasemis_UNIFORM,
title = {{UNIFORM}: A Unified Deep Learning Framework for Multi-organ and Multi-contrast {MRI} Reconstruction},
author = {Yiasemis, George and Ferm, Jonatan and Moriakov, Nikita and Mann, Ritse M. and Sonke, Jan-Jakob and Teuwen, Jonas},
booktitle = {Medical Imaging with Deep Learning},
year = {2025},
url = {https://openreview.net/forum?id=I13Y1nU6gs}
}
@article{Yiasemis_2025_vSHARP,
title = {vSHARP: Variable Splitting Half-quadratic ADMM algorithm for reconstruction of inverse-problems},
author = {Yiasemis, George and Moriakov, Nikita and Sonke, Jan-Jakob and Teuwen, Jonas},
journal = {Magnetic Resonance Imaging},
volume = {115},
pages = {110266},
year = {2025},
doi = {10.1016/j.mri.2024.110266}
}
@article{DIRECTTOOLKIT,
title={DIRECT: Deep Image REConstruction Toolkit},
author={Yiasemis, George and Moriakov, Nikita and Karkalousos, Dimitrios and Caan, Matthan and Teuwen, Jonas},
journal={Journal of Open Source Software},
volume={7},
number={73},
pages={4278},
year={2022},
doi={10.21105/joss.04278}
}