| --- |
| datasets: |
| - AnonRes/OpenMind |
| license: cc-by-4.0 |
| pipeline_tag: image-segmentation |
| tags: |
| - medical |
| --- |
| |
| # OpenMind Benchmark 3D SSL Models (Primus) |
|
|
| This repository hosts pre-trained checkpoints for the **Primus** and **ResEnc-L** backbones from the OpenMind benchmark. |
|
|
| > **Papers**: |
| > - [Primus: Enforcing Attention Usage for 3D Medical Image Segmentation](https://huggingface.co/papers/2503.01835) |
| > - [An OpenMind for 3D medical vision self-supervised learning](https://huggingface.co/papers/2412.17041) |
| > |
| > **Code**: [MIC-DKFZ/nnUNet](https://github.com/MIC-DKFZ/nnUNet) |
| > **Pre-training framework**: [MIC-DKFZ/nnssl](https://github.com/MIC-DKFZ/nnssl) |
| > **Dataset**: [AnonRes/OpenMind](https://huggingface.co/datasets/AnonRes/OpenMind) |
|
|
| --- |
|
|
|  |
|
|
| ## Overview |
|
|
| This repository hosts pre-trained checkpoints from the **OpenMind** benchmark, featuring the **Primus** architecture. Primus is a Transformer-centric segmentation architecture that leverages high-resolution tokens and advances in positional embeddings to achieve state-of-the-art results in 3D medical image segmentation. |
|
|
| Each model was pre-trained using a specific self-supervised learning (SSL) method on the [OpenMind Dataset](https://huggingface.co/datasets/AnonRes/OpenMind), a standardized collection of public brain MRI datasets. |
|
|
| **Note**: These models are intended to be used as weights for downstream fine-tuning for **segmentation** tasks using the [nnU-Net framework](https://github.com/MIC-DKFZ/nnUNet). |
|
|
| --- |
|
|
| ## Model Variants |
|
|
| We release SSL checkpoints for two backbone architectures: |
|
|
| - **Primus-M**: A transformer-based encoder introduced in the [Primus paper](https://huggingface.co/papers/2503.01835). |
| - **ResEnc-L**: A CNN-based encoder. |
|
|
| Each encoder has been pre-trained using one of the following SSL techniques: |
|
|
| | Method | Description | |
| |---------------|-------------| |
| | [Volume Contrastive (VoCo)](https://arxiv.org/abs/2402.17300) | Contrastive pretraining method for 3D volumes | |
| | [VolumeFusion (VF)](https://arxiv.org/abs/2306.16925) | Spatial volume fusion-based segmentation SSL method | |
| | [Models Genesis (MG)](https://www.sciencedirect.com/science/article/pii/S1361841520302048) | Reconstruction and denoising based pretraining method | |
| | [Masked Autoencoders (MAE)](https://arxiv.org/abs/2111.06377) | Default reconstruction based pretraining method | |
| | [Spark 3D (S3D)](https://arxiv.org/abs/2410.23132) | Sparse reconstruction based pretraining method (CNN only) | |
| | [SimMIM](https://arxiv.org/abs/2111.09886) | Simple masked reconstruction based pretraining method (TR only) | |
| | [SwinUNETR SSL](https://arxiv.org/abs/2111.14791) | Rotation, Contrastive and Reconstruction based pre-training method. | |
| | [SimCLR](https://arxiv.org/abs/2002.05709) | Transfer of 2D Contrastive learning baseline method to 3D | |
|
|
| ## Citation |
|
|
| ```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, Jonathan and Ziegler, Sebastian and Nohel, Michal and Peretzke, Robin eand Köhler, Gregor and Maier-Hein, Klaus H}, |
| journal={arXiv preprint arXiv:2412.17041}, |
| year={2024} |
| } |
| ``` |
