Dataset Overview
Definition：Limb Fracture X-Ray Imaging Datasetis provided byChangsha Langhui Information Technology Co., Ltd.The large-scale X-ray image database of fractures of four limbs, constructed by Long Salang Langhui Information Technology Ltd., is constructed. The upper limb (scap/scap/grave/foot gill/ wrist/hand) and lower limb (sip/gull/Ke/Keal/ ankle/foot) are covered by fractures, which contain standard positions such as the straight side/slash, which are accompanied by AO/OTA subtype, degree of movement, angles and indications of treatment programmes.
| Dataset Name | Limb Fracture X-Ray Imaging Dataset |
| Total Data Volume | Total X-Ray Volume Included: 1,700,000 Cases |
| Imaging Modality | X-Ray (DR/CR) |
| Covered Body Parts | Upper limb: shoulder/bone/breath/foot gill/brain/hand; lower limb: hip/gullbone/Klept/glick/foot |
| Raw Data | Desensitive original DICOM, retain exposure parameters, pixel spacing, position/view |
| Model | AO/OTA fractured fraction system |
| Quantified Notation | Diversion (mm), angle (°), reduction/rotation malformation |
| Pre-Operative / Post-Operative | Post-Operative Data Accounts for ≤10% |
| Source Institution | Co-operation Sanctuary/Emergency Radiology Section |
| Use Cases | Disruption AI detection and styling, emergency intelligence separation, remote radio-aided diagnosis |
Delivery Specifications and Field Requirements
The data set strictly follows the XR-EXTEREMITY uniform delivery index requirements to ensure data quality and traceability.
Delivery & Counting：One per line for a quadrature fracture examination/Study; one multi-series/multi-view case only
Coverage：Covers fractures of the parts of the arcular section of the limbs, with a standard position such as a positive side/slash
Positives and Composition：Identify fractures as subjects; regular control, post-operative review and quality restricted examination are organized separately
Dedicated Fields：Fractures, fracture type (cross/slash/scrolling/crush/mix/interpolation/condensation), AO/OTA sub-form, transposition/angle/rotation, internal/outside fixation, complications
Cross-Data Association：Priority is given to CT, surgical records, pathology and follow-up; automatic tests should not be used as a final report by a physician
2026 Frontier AI Research Progress
Domain Review：In 2025-2026, vision-language models (VLM) achieved an accuracy of 83 in limb fracture detection.0%, AI assistance significantly improves emergency fracture diagnostic performance, and research is evolving from simple detection to automated fracture classification。
AI-assisted quad fracture detection Meta analysis
2025The system overview and Meta analysis showed that AI-assisted significantly enhanced the diagnostic performance of clinical doctors in the test of limb and torso fractures.
Visual language model, edible plaster fracture test.
PLOS ONE, 2025The potential of VLM in fractures is verified by comparing the performance of ChatGPT-4o, Gemini 2.0, Claude 3.5 in the fracture detection of the pediatric larvae and Gartland sub-form.
Time series repetitivity assessment for fracture images
2025ChatGPT-5.2 accurate rate 83.0 per cent (70.0 per cent sensitivity, 96.0 per cent specificity) and Gemini 3 Pro accurate rate 77.7 per cent, providing a new paradigm for forensic radiology and fracture automation.
AI optimizes the detection and classification of fractures of the backbone of the thiram bone
Informatics in Medicine Unlocked, 2026Integration of AI and in-depth learning into X-ray image analysis for automatic detection and classification of fractures of the backbone of the thiram.
Annotation Workflow & Quality Control
Image Acquisition & De-identification
Standardized acquisition workflow: complete data is exported directly from the equipment, and patient identifying information (PHI) is removed before the data is stored。
Initial Annotation (Specialist Physician)
Attending physicians annotate case by case against the standards, including lesion localization, morphological description and disease term determination。
Review (Associate Chief Physician or Above)
Experts with the title of Associate Chief Physician or above review the initial annotation results item by item, correcting erroneous annotations and supplementing missing dimensions。
Consistency Assessment
10% of samples are randomly selected and independently annotated by 3 physicians to calculate Fleiss' Kappa; below 0.Dimensions scored 75 are flagged for rework。
License and Usage Agreement
Academic Research License
For universities and research institutions, supporting academic research related to medical AI。After signing the agreement, a de-identified data subset is provided; the source must be acknowledged：Langhui Technology DataAssetsAPI。
Commercial License
For medical device companies and AI diagnostics companies, supporting medical AI product R&D and medical device registration。Provides full datasets + custom annotation + incremental update services。
Data Compliance Statement
All images come from legally authorized sources; PHI fields are fully de-identified and contain no information that can directly identify an individual, in compliance with the Personal Information Protection Law and the Data Security Law。
Customized services
Supports extended requirements such as adding specific disease types, multimodal annotation expansion, and custom training of AI-assisted diagnostic models。
Quick Facts
AI Frontier Research
In 2025-2026, vision-language models (VLM) achieved an accuracy of 83 in limb fracture detection.0%, AI assistance significantly improves emergency fracture diagnostic performance, and research is evolving from simple detection to automated fracture classification。