Related Experiment Video
Updated: Jun 9, 2026
10:30
Sequential In vivo Imaging of Osteogenic Stem/Progenitor Cells During Fracture Repair
Published on: May 23, 2014
10.5K
Deep Learning Model Based on You Only Look Once Algorithm for Detection and Visualization of Fracture Areas in
Young-Dae Jeon1, Min-Jun Kang2, Sung-Uk Kuh2
1Department of Orthopedic Surgery, University of Ulsan College of Medicine, Ulsan University Hospital, Ulsan 44033, Republic of Korea.
Diagnostics (Basel, Switzerland)
|January 11, 2024
Summary
This study introduces an AI system using YOLO v4 for accurate fracture detection in 3D bone images. The system enhances diagnostic accuracy and speed for orthopedic surgeons.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Orthopedics
Background:
- Fracture detection and diagnosis are critical in orthopedic care.
- Current methods can be time-consuming and prone to errors.
- AI offers potential to improve diagnostic accuracy and efficiency.
Purpose of the Study:
- To develop and evaluate an AI-powered system for enhanced fracture detection and diagnosis.
- To assist orthopedic surgeons in making more accurate and intuitive diagnostic decisions.
- To reduce errors in fracture diagnosis using advanced AI models.
Main Methods:
- Utilized the YOLO v4 (You Only Look Once version 4) AI model for object detection.
- Employed CSPDarkNet-53, Spatial Pyramid Pooling, and Path Aggregation Network for feature extraction.
- Mapped YOLO v4 bounding boxes onto 3D reconstructed bone images from CT scans.
- Visualized fractures using a red mask overlaid on 3D images.
Main Results:
- Achieved high average precision (AP) values: 0.71 for tibia and 0.81 for elbow fractures.
- Calculated Intersection over Union (IoU) values of 0.6327 for tibia and 0.6638 for elbow.
- Demonstrated an intuitive display of fractured areas on 3D bone models.
Conclusions:
- The YOLO v4-based AI system shows significant promise for accurate fracture detection.
- The 3D visualization with AI support can aid in quick and precise trauma diagnosis.
- This AI-powered system has the potential to improve clinical decision-making in orthopedics.
Keywords:
YOLO v4deep learningfracture detectionthree dimensional (3D) reconstructed imagetibia and elbowMore Related Videos
Related Concept Videos
01:18Classification of Bones
The bones of the human skeletal system are of varied shapes, sizes, and functions. They can be classified based on their shape and function into four major classes: long bones, short bones, flat bones, and irregular bones. Some classifications include a fifth type, the sesamoid bones, as a separate class, whereas others categorize them under short bones.
Long and Short Bones
The appendicular skeleton, particularly the upper and lower limbs, is primarily made of long and short bones. The long...
Long and Short Bones
The appendicular skeleton, particularly the upper and lower limbs, is primarily made of long and short bones. The long...
01:27Fractures: Bone Repair
Treatment for a fracture is based on the type of break, the bone affected, and the patient's age.
Minor fractures with no bone displacement are treated by immobilizing the fractured bone using a cast or splint. However, in the case of fractures with displaced bones, the broken bones are repositioned before immobilization to ensure successful healing without deformation and loss of function. The realignment of fractured bone ends is performed through a process called reduction. If the procedure...
Minor fractures with no bone displacement are treated by immobilizing the fractured bone using a cast or splint. However, in the case of fractures with displaced bones, the broken bones are repositioned before immobilization to ensure successful healing without deformation and loss of function. The realignment of fractured bone ends is performed through a process called reduction. If the procedure...