README.md

---
license: mit
tags:
- medical
- mri
- pet
- brain-image-analysis
- multimodal
- alzheimer
arxiv: 2605.13059
---

# BrainAnytime Checkpoints

Finetuned checkpoints for **BrainAnytime: Anatomy-Aware Cross-Modal Pretraining for Brain Image Analysis with Arbitrary Modality Availability**.

## Paper

- **Title:** BrainAnytime: Anatomy-Aware Cross-Modal Pretraining for Brain Image Analysis with Arbitrary Modality Availability
- **arXiv:** [2605.13059](https://arxiv.org/abs/2605.13059)
- **PDF:** [https://arxiv.org/pdf/2605.13059](https://arxiv.org/pdf/2605.13059)

## Model Sources

- **Repository:** https://github.com/guangqianyang/BrainAnytime
- **Paper:** https://arxiv.org/abs/2605.13059
- **Demo:** https://huggingface.co/spaces/Simmonstt/BrainAnytime-Demo

## Checkpoints

| File | Task | Type |
|------|------|------|
| `CN_vs_AD_seed_0_best.pth` | CN vs AD | Classification |
| `CN_vs_MCI_seed_0_best.pth` | CN vs MCI | Classification |
| `MMSE_seed_0_best.pth` | MMSE | Regression |
| `AGE_seed_0_best.pth` | AGE | Regression |

## Usage

```python
from huggingface_hub import hf_hub_download

ckpt = hf_hub_download(
    repo_id="Simmonstt/BrainAnytime",
    filename="CN_vs_AD_seed_0_best.pth",
)
```

## Citation

If you use these checkpoints, please cite:

```bibtex
@misc{yang2026brainanytimeanatomyawarecrossmodalpretraining,
      title={BrainAnytime: Anatomy-Aware Cross-Modal Pretraining for Brain Image Analysis with Arbitrary Modality Availability},
      author={Guangqian Yang and Tong Ding and Wenlong Hou and Yue Xun and Ye Du and Qian Niu and Shujun Wang},
      year={2026},
      eprint={2605.13059},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2605.13059},
}
```

Paper page: https://arxiv.org/abs/2605.13059