Multi-scanner lumbar spine MRI segmentation database
Multi-scanner and multi-modal lumbar vertebral body and intervertebral disc segmentation database
Clinical lumbar spine MRI of 34 patients from 55 sessions on Philips, Siemens and GE scanners, with T1w, contrast T1w, T2w, Dixon and STIR series and manual masks of the L1 to L5 vertebral bodies and four discs, for multi-domain spine segmentation.
Overview
This database holds routine lumbar spine MRI from patients of the Klinikum rechts der Isar in Munich, with manual masks of the lumbar vertebral bodies and intervertebral discs. It was assembled by radiologists at the Technical University of Munich together with Eindhoven University of Technology. Its purpose is to train and test segmentation methods that have to cope with images from different scanners and pulse sequences, rather than from one tuned protocol.
Composition
There are 34 adult patients (20 female, 14 male) aged 30 to 88 years. They were scanned for low back pain or radiculopathy, follow-up after resection of a spinal tumour, known cancer with suspected spinal metastases, spondylodiscitis or other inflammation, and in one case a sacral fracture. Twenty-one patients have a second session on another scanner model or with another protocol, between two weeks and five years after the first, which gives 55 sessions. Every session has a non-contrast sagittal T1-weighted series. Depending on the session there are also contrast-enhanced T1-weighted, fat-saturated contrast T1-weighted, T2-weighted, STIR and T2-weighted Dixon series; for Dixon the water, fat and in-phase images are separate files. A spreadsheet lists sex, age, indication, scanner and sequences per patient.
Acquisition
Scans date from August 2014 to October 2019, partly from the hospital's own scanners and partly transferred from other institutions. About 71% of sessions come from Philips systems (Achieva, Ingenia, Elition), about 27% from seven Siemens models and one from a GE Signa. Each patient has at least one Philips session with a reference sagittal T1 and a T2 Dixon turbo spin echo protocol at roughly 0.8 x 1 x 3 mm voxels. All images are NIfTI files.
Annotations
A medical doctor outlined the vertebral bodies L1 to L5 and the discs L1/2 to L4/5 by hand in the sagittal plane of the non-contrast T1 images in MITK, under the supervision of a radiologist with eleven years of experience. Posterior elements are excluded. The other series of each patient were registered to that T1 image and resampled into its space, so every volume comes with nine binary masks, one per structure.
Known limitations
- Small cohort from one hospital, with mixed clinical indications.
- Field strength is not reported.
- Labels exist only in the T1 space; other series were resampled with linear interpolation, which smooths them.
- One annotator; no inter-rater agreement is given.
Cohort
Aggregate numbers from the sources below. Bars are relative to the 34 subjects.
Sex
- Female 20 59%
- Male 14 41%
Age
mean 60.4± 15.2 · range 30 to 88.1Contrast combinations
How many subjects have exactly each set of contrasts.
| T1w | T1w_ce | T2w | STIR | Subjects with exactly this set |
|---|---|---|---|---|
18 | ||||
9 | ||||
4 | ||||
3 |
Contrast / sequence
subjects, values can overlap
- T1-weighted 34 100%
- T2-weighted 34 100%
- T1-weighted, contrast enhanced 22 65%
- STIR 7 21%
Condition
subjects, values can overlap
- Low back pain 14 41%
- Discitis 4 12%
- Bone fracture 1 3%
Scanner vendor
subjects
- Philips 34 100%
- Siemens Healthineers 15 44%
- GE HealthCare 1 3%
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
Creative Commons Attribution 4.0 International
Use, share and adapt the data for any purpose, including commercial use, as long as you credit the creators.
What you can do
- Yes
- Yes
- Yes
- Yes
What you can share
- Yes
- Yes
- Yes
What you must do
- Yes
- Share alike No
- No
- No
- Manuscript review No
- Release code No
- Return results No
- Delete after use No
Limits
- No
- Location limits No
Citation
Al Khalil Y, Becherucci EA, Kirschke JS, Karampinos DC, Breeuwer M, Baum T, Sollmann N. Multi-scanner and multi-modal lumbar vertebral body and intervertebral disc segmentation database. Sci Data 9, 97 (2022). https://doi.org/10.1038/s41597-022-01222-8
@article{alkhalil2022,
title = {Multi-scanner and multi-modal lumbar vertebral body and intervertebral disc segmentation database},
author = {Al Khalil, Yasmina and Becherucci, Edoardo A. and Kirschke, Jan S. and Karampinos, Dimitrios C. and Breeuwer, Marcel and Baum, Thomas and Sollmann, Nico},
journal = {Scientific Data},
volume = {9},
pages = {97},
year = {2022},
doi = {10.1038/s41597-022-01222-8}
} All numbers
Every number on this page, as stored in stats.csv, with its source.
| Measure | Breakdown | Value | Source |
|---|---|---|---|
| Subjects | total | 34 | alkhalil2022 Methods: Patient cohort |
| Studies | total 34 first sessions plus 21 follow-up sessions on a different scanner model or protocol, counted from the per-patient rows | 55 | alkhalil2022 Tables 2 and 3 |
| Subjects | sex=female counted from the per-patient rows; the text gives 58.8% female | 20 | alkhalil2022 Table 1 |
| Subjects | sex=male counted from the per-patient rows | 14 | alkhalil2022 Table 1 |
| Mean age | total | 60.4 | alkhalil2022 Methods: Patient cohort |
| Age SD | total | 15.2 | alkhalil2022 Methods: Patient cohort |
| Minimum age | total | 30 | alkhalil2022 Methods: Patient cohort |
| Maximum age | total | 88.1 | alkhalil2022 Methods: Patient cohort |
| Subjects | age=30-39 counted from the per-patient ages | 3 | alkhalil2022 Table 1 |
| Subjects | age=40-49 counted from the per-patient ages | 7 | alkhalil2022 Table 1 |
| Subjects | age=50-59 counted from the per-patient ages | 7 | alkhalil2022 Table 1 |
| Subjects | age=60-69 counted from the per-patient ages | 5 | alkhalil2022 Table 1 |
| Subjects | age=70-79 counted from the per-patient ages | 8 | alkhalil2022 Table 1 |
| Subjects | age=80-89 counted from the per-patient ages | 4 | alkhalil2022 Table 1 |
| Subjects | condition=low_back_pain indication code 2: low back pain with or without radiculopathy from suspected degeneration; some rows list radiculopathy only | 14 | alkhalil2022 Table 1 |
| Subjects | condition=discitis rows with spondylodiscitis; a fifth patient in the same indication group was imaged for follow-up of an inflammatory lesion | 4 | alkhalil2022 Table 1 |
| Subjects | condition=fracture sacral fracture | 1 | alkhalil2022 Table 1 |
| Subjects | contrast=T1w non-contrast T1-weighted series; the masks were drawn on these | 34 | alkhalil2022 Tables 2 and 3 |
| Subjects | contrast=T2w T2-weighted TSE or T2-weighted Dixon series | 34 | alkhalil2022 Tables 2 and 3 |
| Subjects | contrast=T1w_ce contrast-enhanced T1-weighted series including one fat-saturated series | 22 | alkhalil2022 Tables 2 and 3 |
| Subjects | contrast=STIR | 7 | alkhalil2022 Tables 2 and 3 |
| Subjects | contrast_set=T1w+T1w_ce+T2w union over both sessions, counted from the per-patient rows | 18 | alkhalil2022 Tables 2 and 3 |
| Subjects | contrast_set=T1w+T2w union over both sessions, counted from the per-patient rows | 9 | alkhalil2022 Tables 2 and 3 |
| Subjects | contrast_set=STIR+T1w+T1w_ce+T2w union over both sessions, counted from the per-patient rows | 4 | alkhalil2022 Tables 2 and 3 |
| Subjects | contrast_set=STIR+T1w+T2w union over both sessions, counted from the per-patient rows | 3 | alkhalil2022 Tables 2 and 3 |
| Subjects | vendor=philips every patient had at least one session on a Philips system | 34 | alkhalil2022 Methods: Patient cohort |
| Subjects | vendor=siemens counted from the per-patient rows | 15 | alkhalil2022 Tables 2 and 3 |
| Subjects | vendor=ge | 1 | alkhalil2022 Tables 2 and 3 |
| Studies | vendor=philips 70.9% of sessions; Achieva, Ingenia and Elition | 39 | alkhalil2022 Methods: Magnetic resonance imaging |
| Studies | vendor=siemens 27.3% of sessions; seven scanner models | 15 | alkhalil2022 Methods: Magnetic resonance imaging |
| Studies | vendor=ge one Signa session | 1 | alkhalil2022 Methods: Magnetic resonance imaging |
Sources
The keys used in the table above.
- alkhalil2022 Al Khalil et al. 2022, Scientific Data 9, 97 paper
- osf-qx5rt OSF project page and wiki of the database website