MFXR: X-Ray Images for AI Diagnosis of Monteggia Fractures

4,586 X-ray images from 1,482 patients, including 2,793 Monteggia fracture images and 1,793 normal or other fracture controls. The dataset was created by Ning Li and published on figshare in 2026 to facilitate AI-based diagnostic research. All cases were annotated and validated by board-certified orthopedic surgeons.

Use Cases

• Training AI models for Monteggia fracture detection based on annotated X-ray images.
• Benchmarking model performance against provided baseline results from eight deep learning models.
• Studying radiographic features of subtle fractures to reduce diagnostic errors.

Strengths

• Contains 4,586 X-ray images with high-quality labels validated by board-certified orthopedic surgeons.
• Provides benchmark results from eight representative deep learning models for performance comparison.
• Specifically addresses a clinical gap with a dedicated dataset for a fracture type with a high missed diagnosis rate.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• The geographic and institutional source of the patient images is unknown, which may limit generalizability.
• Freshness should be verified as the last update date is in the future (2026-05-11).

Provenance

Source

figshare

Collection Method

Collection and annotation process is described, but specific source institutions are unknown.

Freshness

Last updated 2026-05-11 09:03:42