Medical imaging dataset · MRI
Spine and joint MRI from a routine outpatient population.
Six hundred musculoskeletal MRI studies dominated by lumbar spine, knee and shoulder, acquired on 1.5T and 3T Siemens systems with standard multi-sequence protocols. Nearly three quarters carry a radiologist report. Part of a wider MRI corpus of more than nine hundred studies that also covers brain, abdomen, pelvis and prostate.
- 600+
- Studies
- 115K+
- DICOM images
- 72%
- With radiologist report
- 93%
- Acquired at 1.5T
- 46%
- Lumbar spine
- ~100%
- Lossless compression
Rounded inventory figures as of October 2026. Counts move as studies are indexed and qualified; exact eligible counts are returned against your specification.
Composition
Who is in the data
Demographics are carried as bands and recorded on every study profile, so a specification can include, exclude or balance by age and sex before anything is packaged.
Patient sex
- Male54%
- Female46%
Age band
- 0–174%
- 18–3926%
- 40–5934%
- 60–7932%
- 80+4%
At a glance
- Series
- 5,800+
- Mean images per study
- ~185
- Acquisition years
- 2023 – 2025
- Source institutions
- 8
Percentages are of studies with the attribute recorded. Figures as of October 2026.
Acquisition profile
How the studies were acquired
Every attribute below is read from the DICOM headers and pixel data of each study, not from a catalogue description. These are the fields your specification can test against.
Body region
Lumbar spine 46%
Knee 18%, shoulder 13%, cervical spine 5%, hip 3%, ankle 3%, wrist 2%, with foot and elbow in small numbers.
Field strength
1.5T 93% · 3T 6%
Field strength is recorded per study and can be a specification criterion.
Sequences
Standard multi-sequence protocols
T1 and T2 turbo spin echo, STIR and fat-suppressed sequences in sagittal, axial and coronal planes; sequence inventory is listed per study.
Slice thickness
2.5 – 5 mm in 93%
Conventional 2D acquisitions; thin-slice 3D sequences are present in a small minority.
Scanner fleet
Siemens 95%
MAGNETOM Sempra 89%, MAGNETOM Spectra 6%, Philips Prodiva CS 4%.
Contrast
Almost entirely non-contrast
Fewer than ten contrast-enhanced studies, flagged individually.
Qualification & delivery
Qualified against your specification, not sold by the terabyte
You do not buy the whole collection. You send inclusion criteria, we return the exact count of studies that pass, and only those are de-identified and delivered.
Specification
We turn your inclusion criteria into a machine-checkable requirement set: modality, anatomy, contrast phase, slice thickness, kVp, bit depth, compression, report pairing and demographic constraints.
Index & profile
Every study is read at header and pixel level and profiled on more than thirty attributes, including phase pattern, scanner model, coverage, compression history and report match.
Verdict per study
Each study receives an eligible, review or reject verdict with the exact criterion codes it failed. Studies whose phase cannot be read from metadata go to a radiologist, not a guess.
De-identify & deliver
Eligible studies are de-identified, re-verified, packaged with a hashed manifest and shipped to your bucket in batches. You load your own pass/fail list and we reconcile against it.
Status of this dataset
MRI collections are qualified on sequence inventory rather than kVp and phase: tell us which planes and weightings your model needs and we return the eligible count per body region. The wider MRI corpus, including around 115 brain studies and smaller prostate, abdomen and pelvis subsets, is available on request.
Read how the qualification service worksUse cases
What teams build with mri spine & msk data
Lumbar degenerative disease
Nearly three hundred lumbar spine studies with reports for disc herniation, stenosis and Modic-change models.
Knee internal derangement
Over a hundred knee studies for meniscal, ligament and cartilage models, with reports describing the findings.
Shoulder and rotator cuff
More than eighty shoulder studies covering rotator cuff tears, tendinopathy and labral pathology.
Sequence and protocol recognition
A consistent Siemens platform with per-series sequence metadata for training models that identify weighting, plane and fat suppression.
Pixel-level labels, study-level classification and structured report extraction are available as a clinician-led annotation project. See medical data annotation.
Consent & permitted use
What this data may be used for, stated up front
Every study in the catalogue was obtained under a signed institutional research agreement with the source imaging network, with a data processing agreement on file. The permitted-use scope travels with the data and is written into every delivery manifest.
Permitted purpose
Development, validation and testing of diagnostic AI. Each delivery is matched to a declared purpose before a single study is packaged.
Permitted jurisdictions
United States and India. Deliveries to other jurisdictions require a fresh agreement with the source, which we will tell you plainly if it is not available.
Not permitted
General-purpose or foundation-model pretraining, and onward resale or sublicensing to third parties. We do not sell around the scope of the source agreement.
Retention
Time-limited retention is part of the agreement. Deliveries carry a retention term and we issue destruction certificates when a term ends or a study is withdrawn.
De-identification
DICOM headers are scrubbed to a documented profile, study, series and instance UIDs are remapped through a sealed crosswalk, and studies with burned-in annotation are detected and quarantined rather than shipped.
Provenance
Each batch ships with a hashed manifest, the acceptance verdict for every study and the source-agreement reference, so your counsel can trace the chain of rights.
Need the de-identification methodology and source-agreement summary for a vendor review? Request the compliance pack.
FAQ
MRI Spine & MSK dataset FAQ
Why is the report rate lower than for CT?
Part of the MRI collection arrived through a channel where reports were supplied separately and some could not be matched with certainty. We only pair a report when the match is unambiguous, so the 72% figure is reliable rather than optimistic.
Can I get brain or prostate MRI?
Yes, in smaller numbers: around 115 brain studies, a few dozen prostate studies and small abdomen and pelvis subsets, nearly all at 1.5T or 3T on Siemens systems. Ask and we will qualify them with the same process.
Are 3D sequences available?
Only in a minority of studies. If your model depends on isotropic 3D acquisitions, say so in the specification and we will tell you the eligible count before any commitment.
More datasets
Other collections in the catalogue
CTCT Abdomen & Pelvis
Multiphase CT abdomen & pelvis, qualified study by study.
- 4,300+
- Studies
- 5.8M+
- DICOM images
- 93%
- With radiologist report
CTCT Head
Thin-slice, lossless non-contrast CT head.
- 2,100+
- Studies
- 800K+
- DICOM images
- 90%
- With radiologist report
CTCT Chest
Thin-slice CT chest across an older adult population.
- 1,250+
- Studies
- 950K+
- DICOM images
- 83%
- With radiologist report
Send us your inclusion criteria.
We will return the exact number of studies in this collection that pass, what the rest fail on, and a sample batch your pipeline can load, before any commercial discussion.
Or email [email protected] · Mohali, India