---
license: agpl-3.0
library_name: monai
pipeline_tag: image-segmentation
tags:
  - pytorch
  - unet
  - 3d-segmentation
  - microscopy
  - light-sheet-microscopy
  - neuroscience
  - axon-segmentation
  - synthetic-data
  - domain-randomization
metrics:
  - dice
---

# AxonSynth

Pretrained three-class 3D U-Net for axon segmentation in light-sheet microscopy, trained on domain-randomized synthetic images.

**Code, environment, and documentation:** [github.com/lincbrain/axonsynth](https://github.com/lincbrain/axonsynth)

## Model

- **Architecture:** MONAI 3D U-Net, approximately 4.8 million parameters.
- **Classes:** background, axon shell, and axon interior.
- **Training patches:** 128 × 128 × 128 voxels at 0.8 µm isotropic resolution.
- **Checkpoint:** `best_model.pt`, the main three-class model selected at epoch 136.

Binary axon foreground probability is calculated by summing the shell and interior probabilities.

## Download

Using the Hugging Face CLI:

```bash
hf download edziocodes/axonsynth best_model.pt --local-dir weights
```

## Run inference

Clone the [code repository](https://github.com/lincbrain/axonsynth) and create its environment:

```bash
conda env create -f environment.yml
conda activate axonsynth
```

From the code repository root, run inference on a volume prepared at **0.8 µm isotropic resolution in model axis order**. See the repository README for preparation instructions.

```bash
python inference/infer_lsm.py \
    --input prepared_0p8um.nii.gz \
    --checkpoint weights/best_model.pt \
    --output-dir predictions \
    --segmentation-mode three_class_shell_interior \
    --stitch-device cpu \
    --output-profile binary_focused \
    --threshold 0.5 \
    --require-cuda
```

This command saves the normalized input, foreground probability, binary mask, and inference settings. The threshold is configurable.

## Evaluation

To compare a prediction against a dense ground-truth volume of the same shape, run from the code repository root:

```bash
python tools/evaluate_lsm_case.py \
    --predictions-dir predictions \
    --prefix prepared_0p8um \
    --gt-path ground_truth.nii.gz \
    --threshold 0.5
```

This writes `metrics.json`, `summary.txt`, and true-positive/false-positive/false-negative overlay images to `evaluation/`. The underlying reusable metric functions are in [`paper_analysis/metrics.py`](https://github.com/lincbrain/axonsynth/blob/main/paper_analysis/metrics.py).

## License

This model checkpoint is released under the **GNU Affero General Public License v3.0 (AGPL-3.0)**. See [LICENSE](LICENSE) for the full terms. The source code is available in the [AxonSynth GitHub repository](https://github.com/lincbrain/axonsynth) under the same license.