Spine MRI Scans with Annotated Dystrophic Changes

UniqueData's Spine Segmentation Dataset contains MRI scans of the lumbar spine. The collection includes 5 multi-angle studies with labeled images and accompanying PDF reports, focusing on dystrophic changes like osteophytes and disc protrusions. The dataset was last updated on HuggingFace in October 2025.

Use Cases

• Train image segmentation models to identify specific dystrophic changes like osteophytes or dorsal disc protrusions in MRI scans.
• Develop anomaly detection algorithms to flag abnormal spinal structures using the doctor-labeled images as ground truth.
• Build multimodal models that correlate visual findings in the .dcm files with textual descriptions from the PDF reports.
• Validate object detection models for locating spinal regions or specific pathologies across different imaging angles.

Strengths

• Includes 5 multi-angle MRI studies for a more complete anatomical view.
• Provides doctor-labeled images and accompanying PDF reports for multimodal analysis.

Limitations

• Very small sample size of only 5 studies, limiting statistical power and model generalizability.
• Geographic bias indicated by a 'Regionus' tag, potentially limiting applicability to other populations.

Provenance

Source

UniqueData via HuggingFace.

Collection Method

MRI scans labeled by doctors, with accompanying PDF reports.

Freshness

Last updated on HuggingFace in October 2025.

Geography

Likely United States, based on platform 'Regionus' tag.