segresnet-brats-mlx / README.md
josand's picture
Simplify model card with concise usage and MedMLX branding
3665959 verified
|
Raw History Blame Contribute Delete
1.88 kB
---
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).