{"success":true,"data":{"author":"Jasper W. van der Graaf et al., Radboud University Medical Center (mirrored by MedOtter)","bucketAccessType":"public","bucketName":"MedOtter/SPIDER","bucketPrefix":"","category":"Health & Biomedical","cloudProvider":"huggingface","createdAt":"2026-11-14T14:15:12.210Z","description":"SPIDER is a public lumbar spine MRI segmentation dataset and benchmark from Radboud University Medical Center, published in Scientific Data (van der Graaf et al. 2024). It contains 447 sagittal lumbar spine MRI series from 218 patients with a history of low back pain (196 T1, 210 T2 and 41 T2-SPACE), each with a reference segmentation of the vertebrae, the intervertebral discs and the spinal canal; vertebrae are numbered top-down, discs are labelled from 201 upward, and the canal is label 100. T2-SPACE masks are fully manual; T1 and T2 masks were refined semi-automatically under musculoskeletal radiologist supervision. overview.csv gives per-series metadata and the training (360) and validation (87) split, and radiological_gradings.csv gives per-disc gradings such as Modic changes, Pfirrmann grade and herniation. The hidden challenge test set is not included. This MedOtter repository reproduces the Zenodo v4 release; as measured 2026-11-14 it holds .mha volumes under images/images and masks/masks plus Parquet indexes, about 3.8 GB in all. Read .mha with SimpleITK or itk. Released under CC BY 4.0 on Zenodo; cite van der Graaf et al. 2024.","displayTitle":"SPIDER: lumbar spine MRI segmentation of vertebrae, discs and spinal canal","doi":"10.5281/zenodo.10159290","id":"bbf348a1-679e-5d09-8cd6-9a693e06ec36","license":"CC-BY-4.0","licenseEvidenceUrl":"https://zenodo.org/records/10159290","objectCountEstimate":900,"probeStatus":"ok","referenceUrl":"https://doi.org/10.1038/s41597-024-03090-w","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"MedOtter/SPIDER\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"MedOtter/SPIDER\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=MedOtter, license:cc-by-4.0, size_categories:n<1K, format:parquet, downloads=423"],"format":"mixed","generatedAt":"2026-11-14T14:15:16.659Z","layout":{"example":"data/training-00000-of-00001.parquet","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"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","encoding":"hex","key":"data/training-00000-of-00001.parquet","truncatedAt":512}],"sampleObjects":["data/training-00000-of-00001.parquet","data/validation-00000-of-00001.parquet","images/images/100_t1.mha","images/images/100_t2.mha","images/images/101_t1.mha"],"sidecars":[{"bytes":"---\nlicense: cc-by-4.0\ntask_categories:\n- image-segmentation\ntags:\n- medical\n- mri\n- lumbar-spine\n- segmentation\n- vertebrae\n- intervertebral-disc\n- spinal-canal\nsize_categories:\n- n<1K\nconfigs:\n- config_name: default\n  data_files:\n  - split: training\n    path: data/training-*\n  - split: validation\n    path: data/validation-*\ndataset_info:\n  features:\n  - name: patient_id\n    dtype: string\n  - name: sequence\n    dtype: string\n  - name: series\n    dtype: string\n  - name: subset\n    dtype: string\n  - name: num_vertebrae\n    dtype: int32\n  - name: num_discs\n    dtype: int32\n  - name: sex\n    dtype: string\n  - name: manufacturer\n    dtype: string\n  - name: model\n    dtype: string\n  - name: magnetic_field_strength\n    dtype: float32\n  - name: num_slices\n    dtype: int32\n  - name: shape_zyx\n    list: int32\n  - name: num_label_classes\n    dtype: int32\n  - name: image_middle_slice\n    dtype: image\n  - name: mask_middle_slice\n    dtype: image\n  - name: overlay_middle_slice\n    dtype: image\n  splits:\n  - name: training\n    num_bytes: 35627666\n    num_examples: 360\n  - name: validation\n    num_bytes: 10866295\n    num_examples: 87\n  download_size: 46479041\n  dataset_size: 46493961\n---\n\n# SPIDER — Lumbar Spine Segmentation in MR Images\n\nPublic release of the SPIDER dataset: 218 patients, 447 sagittal lumbar-spine MRI series with reference segmentations of vertebrae, intervertebral discs (IVDs), and spinal canal. Source: van der Graaf et al., *Scientific Data* 11:264 (2024).\n\n## Contents\n\n| Path | Description |\n|------|-------------|\n| `images/images/` | 447 `.mha` MRI volumes — naming `{patient_id}_{t1|t2|t2_SPACE}.mha` (196 T1 + 210 T2 + 41 T2-SPACE) |\n| `masks/masks/`   | 447 `.mha` reference segmentations, one per image |\n| `overview.csv`   | Per-series metadata: subset (training/validation), sex, vendor, sequence parameters, etc. |\n| `radiological_gradings.csv` | Per-IVD radiological gradings (Modic, Pfirrmann, herniation, etc.) |\n\n## Splits\n\nSplit assignment is in `overview.csv` column `subset`:\n\n- **training** — 360 series\n- **validation** — 87 series\n\n(The Grand Challenge hidden test set of 39 patients is **not** included; it is only accessible via https://spider.grand-challenge.org/.)\n\n## Label Scheme (masks)\n\n- Vertebrae: sequential integer labels (numbered top-down)\n- IVDs: labeled by the vertebra immediately above (lowest IVD = 201, next up = 202, ...)\n- Spinal canal: 100\n- Background: 0\n\n## Recommended Ground Truth\n\nUse `masks/masks/`. The 41 T2-SPACE series are the most authoritative tier (fully manual annotation on near-isotropic, higher-resolution voxels). T1/T2 masks were produced by iterative semi-automatic refinement under MSK-radiologist supervision.\n\n## Source\n\n- **Paper**: van der Graaf, J. W., et al. (2024). Lumbar spine segmentation in MR images: a dataset and a public benchmark. *Sci Data* 11, 264. doi:10.1038/s41597-024-03090-w\n- **Original Zenodo**: https://zenodo.org/records/10159290\n- **Grand Challenge**: https://spider.grand-challenge.org/\n- **License**: CC-BY 4.0\n\nThis HuggingFace mirror reproduces the Zenodo v4 release (Nov 2023, modified Mar 2024) without modification.\n","encoding":"utf8","key":"README.md","name":"README.md","size":3153,"truncated":false}],"sourceObjectKey":"data/training-00000-of-00001.parquet","starterCell":"from datasets import load_dataset\nds = load_dataset(\"MedOtter/SPIDER\")\nprint(ds)","starterSamplePath":"data/training-00000-of-00001.parquet","totalObjects":900},"summary":"SPIDER is a public lumbar spine MRI segmentation dataset and benchmark from Radboud University Medical Center, published in Scientific Data (van der Graaf et al. 2024).","title":"SPIDER: lumbar spine MRI segmentation of vertebrae, discs and spinal canal","updatedAt":"2026-11-14T17:31:07.733Z","visibility":"public","websiteUrl":"https://spider.grand-challenge.org/"}}