---
datasets:
- AnonRes/OpenMind
license: cc-by-4.0
pipeline_tag: image-segmentation
tags:
- medical
---

# Primus-M (SimCLR Pre-trained) — OpenMind Benchmark

> **Model from the paper**: [Primus: Enforcing Attention Usage for 3D Medical Image Segmentation](https://huggingface.co/papers/2503.01835)  
> **Benchmark paper**: [An OpenMind for 3D medical vision self-supervised learning](https://arxiv.org/abs/2412.17041)  
> **Pre-training codebase used to create checkpoint**: [MIC-DKFZ/nnssl](https://github.com/MIC-DKFZ/nnssl)  
> **Dataset**: [AnonRes/OpenMind](https://huggingface.co/datasets/AnonRes/OpenMind)  
> **Downstream (segmentation) fine-tuning**: [TaWald/nnUNet](https://github.com/TaWald/nnUNet)

---

![OpenMind](https://huggingface.co/datasets/AnonRes/OpenMind/resolve/main/assets/OpenMindDataset.png)

## Overview

This repository hosts a pre-trained checkpoint from the **OpenMind** benchmark using the **Primus-M** backbone. Primus is a Transformer-centric segmentation architecture designed specifically to maximize the effectiveness of attention mechanisms in 3D medical imaging, surpassing hybrid architectures and competing with state-of-the-art CNNs.

Each model in this benchmark was pre-trained using a particular self-supervised learning (SSL) method on the [OpenMind Dataset](https://huggingface.co/datasets/AnonRes/OpenMind), a large-scale, standardized collection of public brain MRI datasets.

**Note**: These models are primarily intended for downstream fine-tuning. We recommend using the adaptation frameworks for segmentation and classification provided in the [nnU-Net adaptation repository](https://github.com/TaWald/nnUNet).

*While manual download is possible, we recommend using the auto-download feature of the fine-tuning repository by providing the repository URL on Hugging Face instead of a local checkpoint path.*

---

## Model Variants

In the OpenMind benchmark, SSL checkpoints are released for two backbone architectures:

- **ResEnc-L**: A CNN-based encoder [[a](https://arxiv.org/abs/2410.23132), [b](https://arxiv.org/abs/2404.09556)]  
- **Primus-M**: A transformer-based encoder introduced in the [Primus paper](https://huggingface.co/papers/2503.01835).

Each encoder has been pre-trained using various SSL techniques such as SimCLR, Volume Contrastive (VoCo), VolumeFusion (VF), and Masked Autoencoders (MAE). This specific checkpoint uses **SimCLR**.

## Citation

If you use this model, please cite:

```bibtex
@article{wald2025primus,
  title={Primus: Enforcing Attention Usage for 3D Medical Image Segmentation},
  author={Wald, Tassilo and Roy, Saikat and Isensee, Fabian and Ulrich, Constantin and Ziegler, Sebastian and Trofimova, Dasha and Stock, Raphael and Baumgartner, Michael and Köhler, Gregor and Maier-Hein, Klaus},
  journal={arXiv preprint arXiv:2503.01835},
  year={2025}
}

@article{wald2024openmind,
  title={An OpenMind for 3D medical vision self-supervised learning},
  author={Wald, Tassilo and Ulrich, Constantin and Suprijadi, J. and Ziegler, Sebastian and Nohel, M. and Peretzke, R. and others},
  journal={arXiv preprint arXiv:2412.17041},
  year={2024}
}
```