What question did this study set out to answer?

To enhance multi-site bone fracture detection performance and interpretability through a novel deep learning framework.

March 27, 2026Open Access

An Interpretable Hybrid SFNet Deep Learning Framework for Multi-Site Bone Fracture Detection in Medical Imaging

Key Points

To enhance multi-site bone fracture detection performance and interpretability through a novel deep learning framework.
Developed a Hybrid Selective Feature Network (Hybrid SFNet) architecture.
Incorporated multi-scale convolutional feature extraction and semantic flow mechanisms.
Utilized preprocessing techniques like Canny edge detection and data augmentation.
Evaluated model performance on multi-site fracture datasets with different loss configurations.
Achieved 90% accuracy and 94% precision for binary fracture classification.
Improved recall to 85% with class-weighted loss, reducing false negatives significantly.
Cohen’s Kappa reached 0.79 and Matthews Correlation Coefficient (MCC) reached 0.76.

Abstract

Background/Objectives: Accurate bone fracture detection is essential for orthopedic diagnosis and trauma management. Manual interpretation of X-ray or CT images can be time-consuming and may lead to inter-observer variability, particularly in subtle or multi-site fracture cases. This study proposes an interpretable Hybrid Selective Feature Network (Hybrid SFNet) to improve multi-site bone fracture detection performance and boundary localization. Methods: The proposed Hybrid SFNet extends the original SFNet architecture by incorporating multi-scale convolutional feature extraction and a semantic flow mechanism to enhance structural representation and fracture boundary delineation. Preprocessing techniques, including Canny edge detection, normalization, and data augmentation, were applied to improve feature quality. Model interpretability was addressed using Gradient-weighted Class Activation Mapping (Grad-CAM) to visualize regions contributing to predictions. The model was evaluated on publicly available multi-site fracture datasets using both standard and class-weighted loss configurations. Results: For binary fracture classification, the proposed model achieved 90 accuracy, 94% precision, 77% recall, and an F1-score of 85% for fractured cases. When class-weighted loss was applied, recall improved to 85%, reducing false negatives from 145 to 94 cases (approximately 35%). Under the weighted configuration, Cohen’s Kappa reached 0.79 and the Matthews Correlation Coefficient (MCC) reached 0.76. Conclusions: The proposed Hybrid SFNet provides an interpretable and effective framework for multi-site bone fracture detection. The integration of multi-scale feature extraction and semantic flow mechanisms enhances detection performance and boundary localization, while Grad-CAM supports clinical interpretability. These results indicate the model’s potential for supporting clinical decision-making in orthopedic imaging.

Read Full Paperexternally

Perguntar à IA

Bookmark

View Full Paper