A multi-module enhanced YOLOv8 framework for accurate AO classification of distal radius fractures: SCFAST-YOLO
IntroductionCT-based classification of distal ulnar-radius fractures requires precise detection of subtle features for surgical planning, yet existing methods struggle to balance accuracy with clinical efficiency. This study aims to develop a lightweight architecture that achieves accurate AO (Arbei...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-08-01
|
| Series: | Frontiers in Medicine |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmed.2025.1635016/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849233431468179456 |
|---|---|
| author | Yu Wang Haifu Sun Tiankai Jiang JunFeng Shi JunFeng Shi Qin Wang Qin Wang Hongwei Yang Hongwei Yang Yusen Qiao |
| author_facet | Yu Wang Haifu Sun Tiankai Jiang JunFeng Shi JunFeng Shi Qin Wang Qin Wang Hongwei Yang Hongwei Yang Yusen Qiao |
| author_sort | Yu Wang |
| collection | DOAJ |
| description | IntroductionCT-based classification of distal ulnar-radius fractures requires precise detection of subtle features for surgical planning, yet existing methods struggle to balance accuracy with clinical efficiency. This study aims to develop a lightweight architecture that achieves accurate AO (Arbeitsgemeinschaft für Osteosynthesefragen) typing[an internationally recognized fracture classification system based on fracture location, degree of joint surface involvement, and comminution, divided into three major categories: A (extra-articular), B (partially intra-articular), and C (completely intra-articular)] while maintaining real-time performance. In this task, the major challenges are capturing complex fracture morphologies without compromising detection speed and ensuring precise identification of small articular fragments critical for surgical decision-making.MethodsWe propose SCFAST-YOLO framework to address these challenges. Its first contribution is introducing the SCConv module, which integrates Spatial and Channel Reconstruction Units to systematically reduce feature redundancy while preserving discriminative information essential for detecting subtle articular fragments. Secondly, we develop the C2f-Faster-EMA module that preserves fine-grained spatial details through optimized information pathways and statistical feature aggregation. Third, our Feature-Driven Pyramid Network facilitates multi-resolution feature fusion across scales for improved detection. Finally, we implement a Target-Aware Dual Detection Head that employs task decomposition to enhance localization precision.Results and discussionEvaluated on our FHSU-DRF dataset (332 cases, 1,456 CT sequences), SCFAST-YOLO achieves 91.8% mAP@0.5 and 87.2% classification accuracy for AO types, surpassing baseline YOLOv8 by 2.1 and 2.3 percentage points respectively. The most significant improvements appear in complex Type C fractures (3.2 percentage points higher classification accuracy) with consistent average recall of 0.85–0.88 across all fracture patterns. The model maintains real-time inference (52.3 FPS) while reducing parameters, making it clinically viable. Extensive qualitative and quantitative results demonstrate the advantages of our approach. Additionally, we show the broader clinical applications of SCFAST-YOLO in enhancing consistency and efficiency in trauma care. |
| format | Article |
| id | doaj-art-d051c8a50aa34d62a941cb83a879788c |
| institution | Kabale University |
| issn | 2296-858X |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Medicine |
| spelling | doaj-art-d051c8a50aa34d62a941cb83a879788c2025-08-20T05:32:49ZengFrontiers Media S.A.Frontiers in Medicine2296-858X2025-08-011210.3389/fmed.2025.16350161635016A multi-module enhanced YOLOv8 framework for accurate AO classification of distal radius fractures: SCFAST-YOLOYu Wang0Haifu Sun1Tiankai Jiang2JunFeng Shi3JunFeng Shi4Qin Wang5Qin Wang6Hongwei Yang7Hongwei Yang8Yusen Qiao9Department of Orthopaedics, The First Affiliated Hospital of Soochow University, Suzhou, ChinaDepartment of Orthopaedics, The First Affiliated Hospital of Soochow University, Suzhou, ChinaSchool of medicine, Nantong University, Nantong, Jiangsu, ChinaDepartment of Orthopaedics, Affiliated Nantong Hospital 3 of Nantong University, Nantong, ChinaDepartment of Orthopaedics, Nantong Third People's Hospital, Nantong, ChinaDepartment of Orthopaedics, Affiliated Nantong Hospital 3 of Nantong University, Nantong, ChinaDepartment of Orthopaedics, Nantong Third People's Hospital, Nantong, ChinaDepartment of Orthopaedics, Affiliated Nantong Hospital 3 of Nantong University, Nantong, ChinaDepartment of Orthopaedics, Nantong Third People's Hospital, Nantong, ChinaDepartment of Orthopaedics, The First Affiliated Hospital of Soochow University, Suzhou, ChinaIntroductionCT-based classification of distal ulnar-radius fractures requires precise detection of subtle features for surgical planning, yet existing methods struggle to balance accuracy with clinical efficiency. This study aims to develop a lightweight architecture that achieves accurate AO (Arbeitsgemeinschaft für Osteosynthesefragen) typing[an internationally recognized fracture classification system based on fracture location, degree of joint surface involvement, and comminution, divided into three major categories: A (extra-articular), B (partially intra-articular), and C (completely intra-articular)] while maintaining real-time performance. In this task, the major challenges are capturing complex fracture morphologies without compromising detection speed and ensuring precise identification of small articular fragments critical for surgical decision-making.MethodsWe propose SCFAST-YOLO framework to address these challenges. Its first contribution is introducing the SCConv module, which integrates Spatial and Channel Reconstruction Units to systematically reduce feature redundancy while preserving discriminative information essential for detecting subtle articular fragments. Secondly, we develop the C2f-Faster-EMA module that preserves fine-grained spatial details through optimized information pathways and statistical feature aggregation. Third, our Feature-Driven Pyramid Network facilitates multi-resolution feature fusion across scales for improved detection. Finally, we implement a Target-Aware Dual Detection Head that employs task decomposition to enhance localization precision.Results and discussionEvaluated on our FHSU-DRF dataset (332 cases, 1,456 CT sequences), SCFAST-YOLO achieves 91.8% mAP@0.5 and 87.2% classification accuracy for AO types, surpassing baseline YOLOv8 by 2.1 and 2.3 percentage points respectively. The most significant improvements appear in complex Type C fractures (3.2 percentage points higher classification accuracy) with consistent average recall of 0.85–0.88 across all fracture patterns. The model maintains real-time inference (52.3 FPS) while reducing parameters, making it clinically viable. Extensive qualitative and quantitative results demonstrate the advantages of our approach. Additionally, we show the broader clinical applications of SCFAST-YOLO in enhancing consistency and efficiency in trauma care.https://www.frontiersin.org/articles/10.3389/fmed.2025.1635016/fulldistal radius fracturesYOLOv8C2f-Faster-EMATADDHFDPN |
| spellingShingle | Yu Wang Haifu Sun Tiankai Jiang JunFeng Shi JunFeng Shi Qin Wang Qin Wang Hongwei Yang Hongwei Yang Yusen Qiao A multi-module enhanced YOLOv8 framework for accurate AO classification of distal radius fractures: SCFAST-YOLO Frontiers in Medicine distal radius fractures YOLOv8 C2f-Faster-EMA TADDH FDPN |
| title | A multi-module enhanced YOLOv8 framework for accurate AO classification of distal radius fractures: SCFAST-YOLO |
| title_full | A multi-module enhanced YOLOv8 framework for accurate AO classification of distal radius fractures: SCFAST-YOLO |
| title_fullStr | A multi-module enhanced YOLOv8 framework for accurate AO classification of distal radius fractures: SCFAST-YOLO |
| title_full_unstemmed | A multi-module enhanced YOLOv8 framework for accurate AO classification of distal radius fractures: SCFAST-YOLO |
| title_short | A multi-module enhanced YOLOv8 framework for accurate AO classification of distal radius fractures: SCFAST-YOLO |
| title_sort | multi module enhanced yolov8 framework for accurate ao classification of distal radius fractures scfast yolo |
| topic | distal radius fractures YOLOv8 C2f-Faster-EMA TADDH FDPN |
| url | https://www.frontiersin.org/articles/10.3389/fmed.2025.1635016/full |
| work_keys_str_mv | AT yuwang amultimoduleenhancedyolov8frameworkforaccurateaoclassificationofdistalradiusfracturesscfastyolo AT haifusun amultimoduleenhancedyolov8frameworkforaccurateaoclassificationofdistalradiusfracturesscfastyolo AT tiankaijiang amultimoduleenhancedyolov8frameworkforaccurateaoclassificationofdistalradiusfracturesscfastyolo AT junfengshi amultimoduleenhancedyolov8frameworkforaccurateaoclassificationofdistalradiusfracturesscfastyolo AT junfengshi amultimoduleenhancedyolov8frameworkforaccurateaoclassificationofdistalradiusfracturesscfastyolo AT qinwang amultimoduleenhancedyolov8frameworkforaccurateaoclassificationofdistalradiusfracturesscfastyolo AT qinwang amultimoduleenhancedyolov8frameworkforaccurateaoclassificationofdistalradiusfracturesscfastyolo AT hongweiyang amultimoduleenhancedyolov8frameworkforaccurateaoclassificationofdistalradiusfracturesscfastyolo AT hongweiyang amultimoduleenhancedyolov8frameworkforaccurateaoclassificationofdistalradiusfracturesscfastyolo AT yusenqiao amultimoduleenhancedyolov8frameworkforaccurateaoclassificationofdistalradiusfracturesscfastyolo AT yuwang multimoduleenhancedyolov8frameworkforaccurateaoclassificationofdistalradiusfracturesscfastyolo AT haifusun multimoduleenhancedyolov8frameworkforaccurateaoclassificationofdistalradiusfracturesscfastyolo AT tiankaijiang multimoduleenhancedyolov8frameworkforaccurateaoclassificationofdistalradiusfracturesscfastyolo AT junfengshi multimoduleenhancedyolov8frameworkforaccurateaoclassificationofdistalradiusfracturesscfastyolo AT junfengshi multimoduleenhancedyolov8frameworkforaccurateaoclassificationofdistalradiusfracturesscfastyolo AT qinwang multimoduleenhancedyolov8frameworkforaccurateaoclassificationofdistalradiusfracturesscfastyolo AT qinwang multimoduleenhancedyolov8frameworkforaccurateaoclassificationofdistalradiusfracturesscfastyolo AT hongweiyang multimoduleenhancedyolov8frameworkforaccurateaoclassificationofdistalradiusfracturesscfastyolo AT hongweiyang multimoduleenhancedyolov8frameworkforaccurateaoclassificationofdistalradiusfracturesscfastyolo AT yusenqiao multimoduleenhancedyolov8frameworkforaccurateaoclassificationofdistalradiusfracturesscfastyolo |