---
license: apache-2.0
---
This work presents **VoCo**, a new method for Large-Scale 3D Medical Image Pre-training. We release a new benchmark, including **160K** volumes (**42M** slices) for pre-training, **31M~1.2B** params of pre-trained models, various pre-training recipes, and **50+** downstream tasks implementation.

Linshan Wu, Jiaxin Zhuang, and <a href="https://scholar.google.com/citations?hl=en&user=Z_t5DjwAAAAJ">**Hao Chen**</a>. [**"Large-Scale 3D Medical Image Pre-training with Geometric Context Priors"**](https://arxiv.org/abs/2410.09890). CVPR 2024 Extension.

Paper link: https://arxiv.org/abs/2410.09890

Code link: https://github.com/Luffy03/Large-Scale-Medical

## Download Models

```
huggingface-cli download Luffy503/VoCo  --repo-type model --local-dir .  --cache-dir ./cache
```