MedMLX/nnunet-brats-mlx

nnU-Net · Brain Tumor

Segment brain tumor regions from four MRI sequences with the nnU-Net BraTS checkpoint.

GitHub · Files · Docs

Input	Output
T1, T1ce, T2 + FLAIR · NIfTI	Brain tumor segmentation

Apple Silicon · Metal · Python 3.13 / 3.14

Quick start

uv venv --python 3.13
source .venv/bin/activate

uv pip install "nnunet-mlx==0.5.1"
uv tool install huggingface-hub

hf download MedMLX/nnunet-brats-mlx --local-dir models

Replace the example input paths with your own files.

from nnunet_mlx.medmlx import run

result = run(
    model_dir='models',
    image_paths=['T1w.nii.gz', 'T1gd.nii.gz', 'T2w.nii.gz', 'FLAIR.nii.gz'],
    output_dir='outputs',
    folds=[0],
    use_mirroring=False,
    step_fraction=0.5,
)
print(result["outputs"])

Keep all four MRI volumes on the same voxel grid, in the order shown.

Use & license

For research and education. Not validated for clinical use.

Weights: CC-BY-4.0. Notices.