SpineWeb Dataset 11 (anisotropic lumbar MRI)
SpineWeb Dataset 11: High anisotropy MRIs of the lower back
17 anonymized routine lumbar spine MRI volumes (T1, T2 and TIRM) with strongly anisotropic voxels, from several hospitals, with manual vertebral body segmentations as surface meshes. Released by the University of Siegen with its vertebra segmentation code.
Overview
SpineWeb Dataset 11 is a small set of routine clinical MRI scans of the lower back, released by the Computer Graphics and Multimedia Systems Group at the University of Siegen together with the source code of a vertebral body detection and segmentation method. The scans were chosen to reflect what clinics actually acquire: thick slices and in-plane pixels that are much smaller than the slice spacing. SpineWeb listed the release as its Dataset 11 and pointed to the Siegen project page for download.
Composition
17 anonymized MRI series with matching manual segmentations. They are a subset of the 26 lumbar series (22 from patients, 4 from healthy volunteers, 234 vertebral bodies) that the accompanying paper used for evaluation. The paper reports sex, age, sequence, voxel size and pathology for all 26 series in its Table 2, but does not mark which 17 were released, so those breakdowns are not given here. The number of distinct people in the released subset is not stated.
Acquisition
The 26 evaluation series came from 7 hospitals and 9 scanners and include T1-weighted, T2-weighted and TIRM sequences with a range of echo and repetition times. In the evaluation set, slice spacing was 2.7 to 8.2 times the in-plane pixel spacing. The images are distributed as DICOM files.
Annotations
Vertebral bodies were traced by hand in the primary acquisition plane by neurosurgeons or by an experienced user, at 3 to 6 minutes per vertebra. The segmentations are distributed as surface meshes, one per vertebra. The paper also uses the data for diagnosing scoliosis, spondylolisthesis and vertebral fractures from the segmented shapes.
Known limitations
- Small: 17 series, with no published per-series metadata for the released subset alone.
- No license or terms of use are stated for the images; the authors ask users to cite the paper.
- The SpineWeb host did not resolve on 2026-10-09; its description was read from an Internet Archive copy. The Siegen project page and its download links were reachable on that date.
Cohort
Aggregate numbers from the sources below. Bars are relative to the largest value.
Modality
scans
- MRI 17 100%
Anatomy
scans
- Spine 17 100%
License and access
Our reading of the license, not legal advice. Before you use the data, read the original license and confirm that your use is allowed. We take no responsibility for how you use a dataset. Full disclaimer
Download without an account
No published license or data use terms
The data holder has published no license and no data use terms. Any use, sharing or commercial right has to be agreed with the data holder, and nothing can be assumed to be allowed. Default copyright and data protection law still apply.
No license is named for the images or segmentations. The paper states that the program code is released under an open source license, without naming it, and the project page and paper ask users to cite the paper. No license file was found next to the downloads.
What you can do
- Commercial use Not stated
- Train ML models Not stated
- Create derived data Not stated
- Publish results Not stated
What you can share
- Share the data Not stated
- Share derived data Not stated
- Share trained models Not stated
What you must do
- Cite or credit Not stated
- Share alike Not stated
- Sign an agreement Not stated
- Ethics approval Not stated
- Manuscript review Not stated
- Release code Not stated
- Return results Not stated
- Delete after use Not stated
Limits
- No re-identification Not stated
- Location limits Not stated
Citation
Zukić D, Vlasák A, Egger J, Hořínek D, Nimsky C, Kolb A. Robust Detection and Segmentation for Diagnosis of Vertebral Diseases using Routine MR Images. Computer Graphics Forum 33(6), 190-204 (2014).
All numbers
Every number on this page, as stored in stats.csv, with its source.
| Measure | Breakdown | Value | Source |
|---|---|---|---|
| Scans | total 17 of the 26 evaluation datasets were released, each an anonymized MRI series with manual vertebral body segmentations; the SpineWeb page gives the same number | 17 | zukic2014 Section 8.1, Open science |
| Scans | modality=MR | 17 | spineweb-datasets-2024 Dataset 11 |
| Scans | anatomy=spine Lower back (lumbar spine) | 17 | spineweb-datasets-2024 Dataset 11 |
Sources
The keys used in the table above.
- zukic2014 Zukić et al. 2014, Computer Graphics Forum (author version hosted by the University of Siegen) paper
- siegen-spine-page University of Siegen, Spine segmentation and analysis project page website
- spineweb-datasets-2024 SpineWeb Datasets page, Dataset 11 section (Internet Archive copy of 13 June 2024) website