VISTA-3D · CT Segmentation

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

Input	Output
3D CT · NIfTI	Anatomical segmentation

Apple Silicon · Metal · Python 3.13 / 3.14

Quick start

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

repo="https://github.com/MedMLX/mlx-segment-ct"
release="$repo/releases/download/v0.2.1"
uv pip install "$release/mlx_segment_ct-0.2.1-py3-none-any.whl"
uv tool install huggingface-hub

hf download MedMLX/vista3d-ct-mlx --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.

Downloads last month: -; Downloads are not tracked for this model. How to track

MLX

Hardware compatibility

Quantized

Model tree for MedMLX/vista3d-ct-mlx

Base model

nvidia/NV-Segment-CT

Finetuned

(3)

this model