Include README.md and add citation infos for architectures, methods, dataset and framework into the checkpoint

README.md

@@ -1,3 +1,52 @@
----
-license: cc-by-4.0
----
+---
+license: cc-by-4.0
+datasets:
+- AnonRes/OpenMind
+pipeline_tag: image-feature-extraction
+tags:
+- medical
+---
+
+# OpenMind Benchmark 3D SSL Models
+
+> **Model from the 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 pre-trained checkpoints from the **OpenMind** benchmark:  
+📄 **"An OpenMind for 3D medical vision self-supervised learning"**  
+([arXiv:2412.17041](https://arxiv.org/abs/2412.17041)) — the first extensive benchmark study for **self-supervised learning (SSL)** on **3D medical imaging** data.
+
+The models were pre-trained using various SSL methods on the [OpenMind Dataset](https://huggingface.co/datasets/AnonRes/OpenMind), a large-scale, standardized collection of public brain MRI datasets.
+
+**These models are not recommended to be used as-is.** Instead we recommend using the downstream fine-tuning pipelines for **segmentation** and **classification**, available in the [adaptation repository](https://github.com/TaWald/nnUNet).
+*While direct download is possible, we recommend using the auto-download of the respective fine-tuning repositories.*
+
+---
+
+## 🧠 Model Variants
+
+We release SSL checkpoints for two backbone architectures:
+
+- **ResEnc-L**: A CNN-based encoder [[link1](https://arxiv.org/abs/2410.23132), [link2](https://arxiv.org/abs/2404.09556)]  
+- **Primus-M**: A transformer-based encoder [[Primus paper](https://arxiv.org/abs/2503.01835)]
+
+Each encoder has been pre-trained using the following SSL techniques:
+
+| Method        | Description |
+|---------------|-------------|
+| [Volume Contrastive (VoCo)](https://arxiv.org/abs/2402.17300) | Global contrastive learning in 3D volumes |
+| [VolumeFusion (VF)](https://arxiv.org/abs/2306.16925)         | Spatial fusion-based SSL |
+| [Models Genesis (MG)](https://www.sciencedirect.com/science/article/pii/S1361841520302048) | Classic 3D self-reconstruction |
+| [Masked Autoencoders (MAE)](https://openaccess.thecvf.com/content/CVPR2022/html/He_Masked_Autoencoders_Are_Scalable_Vision_Learners_CVPR_2022_paper) | Patch masking and reconstruction |
+| [Spark 3D (S3D)](https://arxiv.org/abs/2410.23132) | 3D adaptation of Spark framework |
+| [SimMIM](https://openaccess.thecvf.com/content/CVPR2022/html/Xie_SimMIM_A_Simple_Framework_for_Masked_Image_Modeling_CVPR_2022_paper.html) | Simple masked reconstruction |
+| [SwinUNETR SSL](https://arxiv.org/abs/2111.14791) | Transformer-based pre-training |
+| [SimCLR](https://arxiv.org/abs/2002.05709) | Contrastive learning baseline |

adaptation_plan.json

@@ -0,0 +1,108 @@
+{
+    "architecture_plans": {
+        "arch_class_name": "PrimusM",
+        "arch_kwargs": null,
+        "arch_kwargs_requiring_import": null
+    },
+    "pretrain_plan": {
+        "dataset_name": "Dataset745_OpenNeuro_v2",
+        "plans_name": "nnsslPlans",
+        "original_median_spacing_after_transp": [
+            1,
+            1,
+            1
+        ],
+        "image_reader_writer": "SimpleITKIO",
+        "transpose_forward": [
+            0,
+            1,
+            2
+        ],
+        "transpose_backward": [
+            0,
+            1,
+            2
+        ],
+        "configurations": {
+            "onemmiso": {
+                "data_identifier": "nnsslPlans_3d_fullres",
+                "preprocessor_name": "DefaultPreprocessor",
+                "spacing_style": "onemmiso",
+                "normalization_schemes": [
+                    "ZScoreNormalization"
+                ],
+                "use_mask_for_norm": [
+                    false
+                ],
+                "resampling_fn_data": "resample_data_or_seg_to_shape",
+                "resampling_fn_data_kwargs": {
+                    "is_seg": false,
+                    "order": 3,
+                    "order_z": 0,
+                    "force_separate_z": null
+                },
+                "resampling_fn_mask": "resample_data_or_seg_to_shape",
+                "resampling_fn_mask_kwargs": {
+                    "is_seg": true,
+                    "order": 1,
+                    "order_z": 0,
+                    "force_separate_z": null
+                },
+                "spacing": [
+                    1,
+                    1,
+                    1
+                ],
+                "patch_size": [
+                    160,
+                    160,
+                    160
+                ]
+            }
+        },
+        "experiment_planner_used": "FixedResEncUNetPlanner"
+    },
+    "pretrain_num_input_channels": 1,
+    "recommended_downstream_patchsize": [
+        160,
+        160,
+        160
+    ],
+    "key_to_encoder": "eva",
+    "key_to_stem": "down_projection",
+    "keys_to_in_proj": [
+        "down_projection.proj"
+    ],
+    "key_to_lpe": "eva.pos_embed",
+    "citations": [
+        {
+            "type": "Architecture",
+            "name": "PrimusM",
+            "bibtex_citations": [
+                "@article{wald2025primus,\n            title={Primus: Enforcing attention usage for 3d medical image segmentation},\n            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 K{\"o}hler, Gregor and Maier-Hein, Klaus},\n            journal={arXiv preprint arXiv:2503.01835},\n            year={2025}\n            }"
+            ]
+        },
+        {
+            "type": "Pretraining Method",
+            "name": "Masked Auto Encoder",
+            "bibtex_citations": [
+                "@article{wald2024openmind,\n    title={An OpenMind for 3D medical vision self-supervised learning},\n    author={Wald, Tassilo and Ulrich, Constantin and Suprijadi, Jonathan and Ziegler, Sebastian and Nohel, Michal and Peretzke, Robin and K{\"o}hler, Gregor and Maier-Hein, Klaus H},\n    journal={arXiv preprint arXiv:2412.17041},\n    year={2024}\n    }\n    "
+            ]
+        },
+        {
+            "type": "Pre-Training Dataset",
+            "name": "OpenMind",
+            "bibtex_citations": [
+                "@article{wald2024openmind,\n    title={An OpenMind for 3D medical vision self-supervised learning},\n    author={Wald, Tassilo and Ulrich, Constantin and Suprijadi, Jonathan and Ziegler, Sebastian and Nohel, Michal and Peretzke, Robin and K{\"o}hler, Gregor and Maier-Hein, Klaus H},\n    journal={arXiv preprint arXiv:2412.17041},\n    year={2024}\n    }\n    "
+            ]
+        },
+        {
+            "type": "Framework",
+            "name": "nnssl",
+            "bibtex_citations": [
+                "@article{wald2024revisiting,\n  title={Revisiting MAE pre-training for 3D medical image segmentation},\n  author={Wald, Tassilo and Ulrich, Constantin and Lukyanenko, Stanislav and Goncharov, Andrei and Paderno, Alberto and Maerkisch, Leander and J{\"a}ger, Paul F and Maier-Hein, Klaus},\n  journal={arXiv preprint arXiv:2410.23132},\n  year={2024}\n}"
+            ]
+        }
+    ],
+    "trainer_name": "BaseEvaMAETrainer_BS8"
+}

checkpoint_final.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8c7c1d4e80dc751e39c96fe7ee3e324a1bdeca3c716e2419dfed340d85cecf0
+size 788449517