Related Experiment Video
Updated: Jun 16, 2026
08:18
Three-Dimensional Reconstruction of Orbital Fractures
Published on: May 16, 2025
200
A Pyramid Deep Feature Extraction Model for the Automatic Classification of Upper Extremity Fractures
1Department of Orthopedics and Traumatology, Elazig Fethi Sekin City Hospital, Elazig 23280, Turkey.
Diagnostics (Basel, Switzerland)
|November 14, 2023
Summary
This study introduces a pyramid deep feature extraction model for classifying musculoskeletal radiographs, achieving high accuracy in upper extremity region identification. The automated analysis shows potential for faster, more precise clinical diagnostics in musculoskeletal imaging.
Area of Science:
- Medical Imaging and Diagnostics
- Artificial Intelligence in Healthcare
- Orthopedics and Musculoskeletal Radiology
Background:
- Accurate diagnosis of musculoskeletal issues is vital for effective healthcare.
- Classification of musculoskeletal radiographs is complex, demanding accuracy and efficiency.
- Automated analysis tools are needed to support clinical decision-making.
Purpose of the Study:
- To develop and evaluate a pyramid deep feature extraction model for automatic classification of musculoskeletal radiographs.
- To accurately classify different upper extremity regions within musculoskeletal radiographs.
- To enhance the efficiency and precision of musculoskeletal diagnostic processes.
Main Methods:
- Utilized a pre-trained EfficientNet B0 convolutional neural network (CNN) for end-to-end training.
- Trained the model on radiographic image patches of varying sizes (224x224 to 28x28).
- Extracted features, applied Neighborhood Component Analysis (NCA) for selection, and Support Vector Machine (SVM) for classification.
Main Results:
- Achieved high classification accuracy rates across various upper extremity regions.
- Specific accuracies include: Elbow (92.04%), Finger (91.19%), Forearm (92.11%), Hand (91.34%), Humerus (91.35%), Shoulder (89.49%), and Wrist (92.63%).
- Demonstrated the model's effectiveness as an auxiliary tool for automatic musculoskeletal radiograph analysis.
Conclusions:
- The proposed deep feature extraction model shows significant potential for accelerating clinical diagnostics.
- Automating radiograph classification can lead to more precise results and improved healthcare services.
- Further research is necessary to validate the model for practical clinical integration and application.
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...
01:19Bones of the Upper Limb: Humerus
The upper limb consists of the arm, forearm, wrist, and hand bones. The humerus is the single bone of the upper arm region. Proximally, it has a large, spherical, smooth head that articulates with the glenoid cavity of the scapula to form the glenohumeral or shoulder joint. The margin of the head is the anatomical neck, a residual epiphyseal plate. Laterally it extends to form bony projections called the greater tubercle and the lesser tubercle. Next to the tubercles is the surgical neck, a...