bone fracture Computer Vision Dataset
About bone fracture Dataset
This project provides a specialized medical imaging resource for the automated detection of skeletal injuries in X-ray scans. As part of the Roboflow 100 benchmark, this pre-trained model and dataset are designed to identify fracture lines and angular deformities, offering a high-performance foundation for orthopedic diagnostic tools.
Ways to use bone fracture
- Emergency Room Triage: Implement the model in hospital intake systems to automatically flag X-rays with suspected fractures, ensuring high-priority patients receive immediate attention from radiologists.
- Clinical Decision Support: Assist orthopedic surgeons by highlighting subtle fracture lines or "messed up" bone angles that may be difficult to spot during a rapid manual review of medical imagery.
- Medical Student Training: Use the annotated dataset to build educational software that helps students practice identifying different types of bone displacements and fracture patterns in a controlled environment.
- Remote Health Diagnostics: Integrate the detection model into telehealth platforms to provide preliminary fracture assessments for patients in rural areas where access to immediate specialized care is limited.
- Automated Radiology Reporting: Streamline the documentation process by automatically generating draft reports that pinpoint the location and angular severity of detected bone injuries for physician verification.
This dataset was originally created by Jason Zhang, Caden Li. To see the current project, which may have been updated since this version, please go here: https://universe.roboflow.com/science-research/science-research-2022:-bone-fracture-detection.
This dataset is part of RF100, an Intel-sponsored initiative to create a new object detection benchmark for model generalizability.
Access the RF100 Github repo: https://github.com/roboflow-ai/roboflow-100-benchmark
Use Free Line, Fracture and Angle Detection API
Powered by general detection model
pip install inference-sdk# 1. Import the library
from inference_sdk import InferenceHTTPClient
# 2. Connect to your workspace
client = InferenceHTTPClient(
api_url="https://serverless.roboflow.com",
api_key="API_KEY"
)
# 3. Run your workflow on an image
result = client.run_workflow(
workspace_name="<YOUR_WORKSPACE>",
workflow_id="<YOUR_WORKFLOW_ID>",
images={
"image": "YOUR_IMAGE.jpg" # Path to your image file
},
parameters={
"classes": "line, fracture, angle, messed_up_angle"
},
use_cache=True # cache workflow definition for 15 minutes
)
# 4. Get your results
print(result)Run on custom image
Drop an image here or click to upload
Tell the agent what you want to build.
Cite This Project
LicenseCC BY 4.0If you use this dataset in a research paper, please cite it using the following BibTeX:
@misc{ bone-fracture-7fylg-rcqqr_dataset,
title = { bone fracture Dataset },
type = { Open Source Dataset },
author = { vkit },
howpublished = { \url{ https://universe.roboflow.com/vkit/bone-fracture-7fylg-rcqqr } },
url = { https://universe.roboflow.com/vkit/bone-fracture-7fylg-rcqqr },
journal = { Roboflow Universe },
publisher = { Roboflow },
year = { 2026 },
month = { may },
note = { visited on 2026-07-29 },
}