MedMLX/vista3d-ct-mlx

VISTA-3D · CT Segmentation

Run automatic whole-volume CT segmentation with NVIDIA NV-Segment-CT and native MLX.

GitHub · Files · Docs · Paper

Input	Output
3D CT · NIfTI	Anatomical segmentation

Apple Silicon · Metal · Python 3.13

Quick start

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

uv pip install "mlx-segment-ct>=0.3.5"
uv tool install huggingface-hub

hf download MedMLX/vista3d-ct-mlx --revision e6f45856b4a59212ca10b44a9ade2e2d672f412b --local-dir models

Replace the example input paths with your own files.

from mlx_segment_ct.medmlx import run

result = run(
    image_path='ct.nii.gz',
    weights_path='models',
    output_dir='outputs',
    segment_all=True,
)
print(result["outputs"])

Use & license

For research and education. Not validated for clinical use.

Weights: NVIDIA Open Model License. Notices.

Paper references

• Original model: VISTA3D: A Unified Segmentation Foundation Model for 3D Medical Imaging.

Citation

If you use MedMLX, please cite the MedMLX paper:

@article{sandoval2026medmlx,
  title   = {MedMLX: On-Device Medical Imaging AI for Apple Silicon},
  author  = {Sandoval, A. and Sandoval, J. and Saleem, A.},
  journal = {medRxiv},
  year    = {2026},
  doi     = {10.64898/2026.10.28.26366762}
}