Blame for README.md

---
license: cc-by-nc-sa-4.0
library_name: pytorch
pipeline_tag: image-classification
tags:
  - medical-imaging
  - breast-ultrasound
  - bi-rads
  - retrieval-augmented-generation
  - vision-language
---

# B-RAD inference checkpoints

Released inference weights for **B-RAD**, an interpretable multimodal
retrieval-augmented diagnosis pipeline for breast ultrasound. B-RAD turns a
single breast ultrasound image into an interpretable BI-RADS assessment by
chaining four modules: BI-RADS-aware retrieval, retrieval-guided few-shot
detection, foundational segmentation, and region-aware classification.

- **Paper**: [npj Digital Medicine (2026)](https://www.nature.com/articles/s41746-026-03272-3)
- **DOI**: [10.1038/s41746-026-03272-3](https://doi.org/10.1038/s41746-026-03272-3)
- **Code**: [github.com/snuh-rad-aicon/B-RAD](https://github.com/snuh-rad-aicon/B-RAD)

## Files

| File | Size | Module | Contents |
|---|---:|---|---|
| `b_rad_clip.pt` | 1.98 GiB | B-RAD-CLIP | VPT-adapted BiomedCLIP image tower, BioLinkBERT-large text tower, both 512-d projection heads, the BI-RADS ordinal heads, and the learned temperature |
| `b_rad_full.pt` | 1.98 GiB | B-RAD-FULL | the same encoder plus the 5-fold BI-RADS classification ensemble (`mlp_heads`) and its per-fold standard scalers |
| `b_rad_det.pt` | 339 MiB  | B-RAD-Det | fold-0 stage-2 detector: ViT-B/16 backbone, OWL-ViT-style detection head, and the four learned class queries |

## Usage

```bash
git clone https://github.com/snuh-rad-aicon/B-RAD && cd B-RAD
conda env create -f environment.yml && conda activate b-rad

bash B-RAD/ckpts/download_weights.sh    # fetches this repo, plus UltraSam.pth
bash B-RAD/scripts/inference_full.sh    # end-to-end on the bundled sample
```

`notebooks/brad_inference_demo.ipynb` runs the same pipeline with a
visualization of every stage. The segmentation module needs its own OpenMMLab
environment; see the repository README.

`UltraSam.pth` for B-RAD-Seg is not hosted here; `download_weights.sh` fetches it
from the [UltraSam](https://github.com/CAMMA-public/UltraSam) authors.

## Where each file is used

```text
B-RAD/
├── B-RAD-CLIP/     infer_retrieval.py   --ckpt  b_rad_clip.pt
├── B-RAD-Det/      inference_single.py  --ckpt  b_rad_det.pt
├── B-RAD-Seg/      infer_bbox.py        --ckpt  UltraSam.pth
├── B-RAD-FULL/     infer_birads.py      --ckpt  b_rad_full.pt
└── ckpts/          download_weights.sh  (puts all four here)
```

## Intended use and limitations

Research use only. These weights are not a medical device and must not be used
for clinical decision making. They were trained on public breast-ultrasound
cohorts plus a single-institution clinical cohort, so performance on other
scanners, populations, or acquisition protocols is not characterized.

## Citation

```bibtex
@article{jang2026interpretable,
  title     = {Interpretable multimodal retrieval augmented diagnosis for breast ultrasound with multinational clinical validation and reader study},
  author    = {Jang, Han and An, Subin and Jung, Sunghyun and Ji, Hye and Kim, Miran and Lee, Soochahn and Choi, Kyu Sung and Ha, Su Min},
  journal   = {npj Digital Medicine},
  year      = {2026},
  publisher = {Nature Publishing Group UK London},
  doi       = {10.1038/s41746-026-03272-3},
  url       = {https://doi.org/10.1038/s41746-026-03272-3}
}
```

## License

[CC BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/), matching
the [code repository](https://github.com/snuh-rad-aicon/B-RAD/blob/main/LICENSE):
non-commercial use only, with attribution, and derivatives under the same
license. Upstream components retain their original licenses: BiomedCLIP,
BioLinkBERT, OWL-ViT, and the `timm` ViT-B/16 initialization.

The methods behind these weights are covered by Korean patent application
**10-2026-0096895**. No patent rights are granted by this license. For
commercial use or licensing, please contact the corresponding author.