README.md

---
license: apache-2.0
library_name: mlx
tags:
- mlx
- native-mlx
- apple-silicon
- medical-imaging
- mri
- brain-tumor
- segmentation
- research
language:
- en
inference: false
pipeline_tag: image-segmentation
base_model: MONAI/brats_mri_segmentation
---

<img src="https://huggingface.co/MedMLX/segresnet-brats-mlx/resolve/main/banner.png" alt="MedMLX — Segment. BRAIN MRI / SEGRESNET" width="100%">

# SegResNet · Brain Tumor

Segment brain tumor regions from four MRI sequences with the MONAI SegResNet checkpoint.

[GitHub](https://github.com/MedMLX/segresnet-mlx) · [Files](https://huggingface.co/MedMLX/segresnet-brats-mlx/tree/main) · [Docs](https://github.com/MedMLX/segresnet-mlx/blob/main/README.md#quick-start)

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

**Apple Silicon · Metal · Python 3.13 / 3.14**

## Quick start

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

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

hf download MedMLX/segresnet-brats-mlx --local-dir models
```

Replace the example input paths with your own files.

```python
from segresnet_mlx.medmlx import run

result = run(
    bundle='brats_mri_segmentation',
    weights_path='models/segresnet-brats.safetensors',
    output_dir='outputs',
    t1c_path='T1gd.nii.gz',
    t1_path='T1w.nii.gz',
    t2_path='T2w.nii.gz',
    flair_path='FLAIR.nii.gz',
)
print(result["outputs"])
```

All four MRI volumes must share the same voxel grid.

## Use & license

For research and education. Not validated for clinical use.

Weights: [Apache-2.0](https://huggingface.co/MedMLX/segresnet-brats-mlx/blob/main/LICENSE). [Notices](https://huggingface.co/MedMLX/segresnet-brats-mlx/blob/main/NOTICE).