FracFusionNet: A Multi-Level Feature Fusion Convolutional Network for Bone Fracture Detection in Radiographic Images

Area of Science:

• Medical Imaging
• Artificial Intelligence
• Orthopedics

Background:

• Bone fractures (BFs) are prevalent injuries requiring accurate radiographic diagnosis.
• Manual X-ray evaluation is time-consuming and prone to errors.
• AI, specifically deep learning (DL), offers potential to improve fracture detection accuracy.

Purpose of the Study:

• To develop and evaluate a novel deep learning model for precise bone fracture detection.
• To enhance the efficiency and accuracy of radiographic fracture diagnosis.
• To provide a robust AI solution for clinical settings.

Main Methods:

• A novel Convolutional Neural Network (CNN) model, the Multi-Level Feature Fusion Network (MLFNet), was developed.
• MLFNet integrates low-level and high-level image features for comprehensive analysis.
• The model was trained and validated on the Bone Fracture Multi-Region X-ray (BFMRX) dataset with preprocessing and ablation studies.

Main Results:

• MLFNet achieved a standalone accuracy of 99.60% in fracture detection.
• When integrated into hybrid ensembles, MLFNet reached 98.81% accuracy.
• The model demonstrated robustness and generalizability across different data distributions.

Conclusions:

• The proposed MLFNet model offers a timely and precise solution for fracture detection.
• This AI approach optimizes the diagnostic process, potentially reducing healthcare costs.
• MLFNet shows significant promise for aiding clinicians in orthopedics and radiology.