ASC-YOLO: Multi-Scale Feature Fusion and Adaptive Decoupled Head for Fracture Detection in Medical Imaging
Source abstract
Abstract
Fractures occur frequently in daily life, and before a surgeon implements treatment, the plan needs to be based on the radiologist’s imaging diagnosis of the X-ray. Despite progress in deep learning–based fracture detection, existing methods (e.g., two-stage detectors) face challenges such as small target leakage and sensitivity to background interference in complex medical images. To address these issues, this paper proposes the ASC-YOLO model, which employs the Scale-Sensitive Feature Fusion (SSFF) module to enhance multi-scale information extraction through cross-layer feature interaction. In addition, an Adaptive Decoupled Detection Head (AsDDet) is introduced to decouple the classification and regression tasks of the detection head, thereby improving the localization accuracy of small fracture regions and suppressing background noise. Experiments on a large fracture radiograph dataset, GRAZPEDWRI-DX, demonstrate that ASC-YOLO achieves 61% mAP@50, representing an 8% improvement over the baseline YOLO model (mAP@53%). It attains 95% mAP@50 for the fracture category and 97% mAP@50 for the metal category. Furthermore, the model was evaluated on a tumor dataset to verify its generalization capability. The proposed framework provides reliable technical support for accurate fracture screening, which is expected to reduce missed diagnoses and optimize treatment.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Neural Network Applications · COVID-19 diagnosis using AI · Medical Imaging and Analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Computer and Information Science, Chongqing Normal University, Chongqing 401331, China
References (28)
Show source-provided references
1. Assessing the Variability of Antibiotic Management in Patients with Open Hand Fractures Presenting to the Pediatric Emergency Department10.1097/PEC.0000000000002832 ↗
2. Frequently missed fractures in pediatric trauma: A pictorial review of plain film radiography10.1016/j.rcl.2019.02.009 ↗
3. A pediatric wrist trauma x-ray data-set (grazpedwri-dx) for machine learning10.1038/s41597-022-01328-z ↗
4. Sohan, M., Sai Ram, T., and Rami Reddy, C.V. (2024, January 18–20). A review on yolov8 and its advancements. Proceedings of the International Conference on Data Intelligence and Cognitive Informatics, Tirunelveli, India.10.1007/978-981-99-7962-2_39 ↗
5. Wang, C.Y., Yeh, I.H., and Liao, H.Y.M. (October, January 29). Yolov9: Learning what you want to learn using programmable gradient information. Proceedings of the European Conference on Computer Vision, Milan, Italy.
6. Wang, A., Chen, H., Liu, L., Chen, K., Lin, Z., Han, J., and Ding, G. (2024, January 10–15). Yolov10: Real-time end-to-end object detection. Proceedings of the 38th International Conference on Neural Information Processing Systems, Vancouver, BC, Canada.
7. Analyzing the noise robustness of deep neural networks10.1109/TVCG.2020.2969185 ↗
8. Learning a deep multi-scale feature ensemble and an edge-attention guidance for image fusion10.1109/TCSVT.2021.3056725 ↗
9. Li, X., Wang, W., Wu, L., Chen, S., Hu, X., Li, J., Tang, J., and Yang, J. (2020, January 6–12). Generalized focal loss: Learning qualified and distributed bounding boxes for dense object detection. Proceedings of the 4th Conference on Neural Information Processing Systems (NeurIPS 2020), Online.
10. Re-decoupling the classification branch in object detectors for few-class scenes10.1016/j.patcog.2024.110541 ↗
11. AIoU: Adaptive bounding box regression for accurate oriented object detection10.1002/int.22646 ↗
12. Dibo, R., Galichin, A., Astashev, P., Dylov, D.V., and Rogov, O.Y. (2023, January 28–30). Deeploc: Deep learning-based bone pathology localization and classification in wrist X-ray images. Proceedings of the International Conference on Analysis of Images, Social Networks and Texts, Yerevan, Armenia.10.1007/978-3-031-54534-4_14 ↗
13. Ahmed, A., Imran, A.S., Manaf, A., Kastrati, Z., and Daudpota, S.M. (2024). Enhancing Wrist Fracture Detection with YOLO. arXiv.
14. Fracture detection in pediatric wrist trauma X-ray images using YOLOv8 algorithm10.1038/s41598-023-47460-7 ↗
15. YOLOv9 for fracture detection in pediatric wrist trauma X-ray images10.1049/ell2.13248 ↗
16. Medical image data augmentation: Techniques, comparisons and interpretations10.1007/s10462-023-10453-z ↗
17. Gao, Y., Dai, Y., Liu, F., Chen, W., and Shi, L. (2023). An anatomy-aware framework for automatic segmentation of parotid tumor from multimodal MRI. Comput. Biol. Med., 161.10.1016/j.compbiomed.2023.107000 ↗
18. Xu, Z., Zhang, X., Zhang, H., Liu, Y., Zhan, Y., and Lukasiewicz, T. (2023). EFPN: Effective medical image detection using feature pyramid fusion enhancement. Comput. Biol. Med., 163.10.1016/j.compbiomed.2023.107149 ↗
19. Liu, S., Huang, D., and Wang, Y. (2018, January 18–23). Path aggregation network for instance segmentation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.10.1109/CVPR.2018.00913 ↗
20. Ghiasi, G., Lin, T.Y., and Le, Q.V. (2019, January 15–20). NAS-FPN: Learning scalable feature pyramid architecture for object detection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.00720 ↗
21. Huang, H., Chen, Z., Zou, Y., Lu, M., and Chen, C. (2024). Channel prior convolutional attention for medical image segmentation. Comput. Biol. Med., 178.10.1016/j.compbiomed.2024.108784 ↗
22. Kanakis, M., Bruggemann, D., Saha, S., Georgoulis, S., Obukhov, A., and Gool, L.V. (2020, January 23–28). Reparameterizing convolutions for incremental multi-task learning without task interference. Proceedings, Part XX 16, Proceedings of the Computer Vision—ECCV 2020: 16th European Conference, Glasgow, UK.10.1007/978-3-030-58565-5_41 ↗
23. ShuffleNet V2: Practical guidelines for efficient CNN architecture design
24. Wang, C.Y., Bochkovskiy, A., and Liao, H.Y.M. (2022, January 18–24). YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.10.1109/CVPR52729.2023.00721 ↗
25. Liu, B., Liu, X., Jin, X., Stone, P., and Liu, Q. (2021, January 6–14). Conflict-averse gradient descent for multi-task learning. Proceedings of the 35th Conference on Neural Information Processing Systems (NeurIPS 2021), Online.
26. Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., and Savarese, S. (2019, January 15–20). Generalized intersection over union: A metric and a loss for bounding box regression. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.00075 ↗
27. Focal loss for dense object detection10.1109/TPAMI.2018.2858826 ↗
28. Zhao, Y., Lv, W., Xu, S., Wei, J., Wang, G., Dang, Q., Liu, Y., and Chen, J. (2024, January 16–22). Detrs beat yolos on real-time object detection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR52733.2024.01605 ↗