Related Experiment Video
Updated: Jun 30, 2026

Subject-specific Musculoskeletal Model for Studying Bone Strain During Dynamic Motion
Published on: April 11, 2018
Artificial Intelligence Models for Classifying Wrist Ligament Injuries Using Synthetically-Generated Joint Proximity
Hsuan-Yu Chen1, Jon Camp2, Taylor P Trentadue3,4,5
1Orthopedic Biomechanics Research Laboratory, Department of Orthopedics, Mayo Clinic, Rochester, MN, USA.
Artificial intelligence (AI) models trained on synthetic data from finite element models (FEMs) show promise for diagnosing wrist ligament injuries. This approach uses interosseous proximity maps to improve noninvasive diagnostic accuracy.
Area of Science:
- Biomedical Engineering
- Medical Imaging
- Artificial Intelligence
Background:
- Diagnosing wrist ligament injuries is complex, necessitating early detection to prevent osteoarthritis.
- Interosseous proximity maps from volumetric imaging offer insights into wrist joint health.
- Artificial intelligence (AI) can potentially improve noninvasive diagnosis using imaging metrics.
Purpose of the Study:
- To demonstrate the feasibility of training AI models using synthetic data.
- To generate synthetic interosseous proximity map data from finite element models (FEMs).
- To develop AI models for classifying wrist ligament injuries.
Main Methods:
- Personalized wrist FEMs were created from 4D CT data.
- 7,500 injury scenarios generated 9 million synthetic RGB images of proximity vector fields.
- Mixed-input convolutional neural networks (CNNs) were developed and evaluated.
Main Results:
- CNNs achieved an average AUROC of 0.757 across all injury types.
- Performance improved to an average AUROC of 0.824 for clinically relevant angles.
- High sensitivities and specificities (>0.99) were observed in specific simulations.
Conclusions:
- Synthetic FEM data can effectively train AI for wrist ligament injury classification.
- Proximity-based RGB images show potential as biomarkers for ligamentous injury.
Related Concept Videos
Functional Classification of Joints
The functional classification of joints is determined by the amount of mobility between the adjacent bones. Joints are functionally classified as a synarthrosis or immobile joint, an amphiarthrosis or slightly moveable joint, or as a diarthrosis, a freely moveable joint. Fibrous and cartilaginous joints can be functionally classified as either synarthroses or amphiarthroses, whereas all synovial joints are classified as diarthroses.
Synarthrosis
An immobile...
Structural Classification of Joints
A fibrous joint is where the adjacent bones are united by fibrous connective...
Development of the Limb Synovial Joints
The mesenchymal stem cells differentiate into chondrocytes that form the hyaline cartilage, and later the cartilaginous model of the bone. This model further transforms into a bone. This process is known as endochondral ossification.
During development, the limbs...
Ankle Joint
Classification of Bones
Long and Short Bones
The appendicular skeleton, particularly the upper and lower limbs, is primarily made of long and short bones. The long...
Structural Joints: Synovial Joints
