|
|
--- |
|
|
license: mit |
|
|
library_name: pytorch |
|
|
tags: |
|
|
- medical |
|
|
- segmentation |
|
|
- stroke |
|
|
- neurology |
|
|
- mri |
|
|
pipeline_tag: image-segmentation |
|
|
--- |
|
|
|
|
|
# SynthPseudo |
|
|
|
|
|
Synthseg-style model trained on synthetic data derived from OASIS3 tissue maps and ATLAS binary lesion masks. Augmented with pseudo-labels from a private T1w dataset. |
|
|
|
|
|
## Model Details |
|
|
|
|
|
- **Name**: SynthPseudo |
|
|
- **Classes**: 0 (Background), 1 (Gray Matter), 2 (White Matter), 3 (Gray/White Matter Partial Volume), 4 (Cerebro-Spinal Fluid), 5 (Stroke) |
|
|
- **Patch Size**: 192³ |
|
|
- **Voxel Spacing**: 1mm³ |
|
|
- **Input Channels**: 1 |
|
|
|
|
|
## Usage |
|
|
|
|
|
### Loading from Hugging Face Hub |
|
|
|
|
|
```python |
|
|
import torch |
|
|
from synthstroke_model import SynthStrokeModel |
|
|
|
|
|
# Load the model from Hugging Face Hub |
|
|
model = SynthStrokeModel.from_pretrained("liamchalcroft/synthstroke-synth-pseudo") |
|
|
|
|
|
# Prepare your input (example shape: batch_size=1, channels=1, H, W, D) |
|
|
input_tensor = torch.randn(1, 1, 192, 192, 192) |
|
|
|
|
|
# Get predictions (with optional TTA for improved accuracy) |
|
|
predictions = model.predict_segmentation(input_tensor, use_tta=True) |
|
|
|
|
|
# Get tissue probability maps |
|
|
background = predictions[:, 0] # Background |
|
|
gray_matter = predictions[:, 1] # Gray Matter |
|
|
white_matter = predictions[:, 2] # White Matter |
|
|
partial_volume = predictions[:, 3] # Gray/White Matter PV |
|
|
csf = predictions[:, 4] # Cerebro-Spinal Fluid |
|
|
stroke = predictions[:, 5] # Stroke lesion |
|
|
|
|
|
# Alternative: Get logits without TTA |
|
|
logits = model.predict_segmentation(input_tensor, apply_softmax=False) |
|
|
``` |
|
|
|
|
|
## Citation |
|
|
|
|
|
[Machine Learning for Biomedical Imaging](https://www.melba-journal.org/papers/2025:014.html) |
|
|
|
|
|
```bibtex |
|
|
@article{chalcroft2025synthetic, |
|
|
title={Synthetic Data for Robust Stroke Segmentation}, |
|
|
author={Chalcroft, Liam and Pappas, Ioannis and Price, Cathy J. and Ashburner, John}, |
|
|
journal={Machine Learning for Biomedical Imaging}, |
|
|
volume={3}, |
|
|
pages={317--346}, |
|
|
year={2025}, |
|
|
publisher={Machine Learning for Biomedical Imaging}, |
|
|
doi={10.59275/j.melba.2025-f3g6}, |
|
|
url={https://www.melba-journal.org/papers/2025:014.html} |
|
|
} |
|
|
``` |
|
|
|
|
|
For the original arXiv preprint: |
|
|
|
|
|
[arXiv](https://arxiv.org/abs/2404.01946) |
|
|
|
|
|
```bibtex |
|
|
@article{Chalcroft_2025, |
|
|
title={Synthetic Data for Robust Stroke Segmentation}, |
|
|
volume={3}, |
|
|
ISSN={2766-905X}, |
|
|
url={http://dx.doi.org/10.59275/j.melba.2025-f3g6}, |
|
|
DOI={10.59275/j.melba.2025-f3g6}, |
|
|
number={August 2025}, |
|
|
journal={Machine Learning for Biomedical Imaging}, |
|
|
publisher={Machine Learning for Biomedical Imaging}, |
|
|
author={Chalcroft, Liam and Pappas, Ioannis and Price, Cathy J. and Ashburner, John}, |
|
|
year={2025}, |
|
|
month=aug, pages={317–346} |
|
|
} |
|
|
``` |
|
|
|
|
|
## License |
|
|
|
|
|
MIT License - see the [LICENSE](https://github.com/liamchalcroft/synthstroke/blob/main/LICENSE) file for details. |
|
|
|
