Multi-Version Evaluation of Deep Learning Architectures for Tibial Plateau Fracture Detection and Deployment in a Web-Based Clinical Support System.
Authors
Affiliations (7)
Affiliations (7)
- Department of Orthopaedics, Taichung Veterans General Hospital, Taichung City 407219, Taiwan.
- Department of Industrial Engineering and Enterprise Information, Tunghai University, Taichung City 407224, Taiwan.
- Department of Computer Science, Tunghai University, Taichung City 407224, Taiwan.
- Department of Informatics, Krida Wacana Christian University, Jakarta 11470, Indonesia.
- Department of Post-Baccalaureate Medicine, National Chung Hsing University, Taichung City 40227, Taiwan.
- Research Center for Smart Sustainable Circular Economy, Tunghai University, No. 1727, Sec. 4, Taiwan Boulevard, Taichung City 407224, Taiwan.
- Department of Medical Research, Kuang Tien General Hospital, Taichung City 43304, Taiwan.
Abstract
<b>Background</b>: Tibial plateau fractures are complex knee injuries where timely and accurate diagnosis is critical to preventing long-term disability. In high-pressure emergency settings, the risk of missed fractures (false negatives) remains a significant challenge. <b>Objective</b>: This study aims to develop a robust, clinically safe automated detection model using advanced deep learning architectures. <b>Methods</b>: We utilized a dataset of 1489 real-world clinical X-ray images, annotated by orthopedic surgeons, to train and evaluate five versions of the You Only Look Once (YOLO) algorithm (v8, v9, v10, v11, and v12). A rigorous two-stage evaluation process was implemented. First, an initial screening excluded YOLOv8 and YOLOv10 due to critical detection failures ("background errors"), in which the models failed to detect any object in the target region. Second, a comprehensive performance analysis identified YOLOv11 as the optimal architecture. Based on these results, the YOLOv11 model was integrated into a user-friendly, web-based diagnostic system using the Python Flask framework. <b>Results</b>: The YOLOv11 model achieved the highest Mean Average Precision (mAP) of 99.3% and an Accuracy of 98.32%. Crucially for clinical safety, YOLOv11 demonstrated superior sensitivity (96.58%) with the lowest false negative rate, attributed to its enhanced feature aggregation capabilities which effectively distinguish subtle fracture lines from trabecular bone patterns. Independent web interface validation (n = 109 real-world cases) confirmed 98.17% accuracy, 98.00% sensitivity, 98.31% specificity, 98.00% Positive Predictive Value (PPV), and 98.31% Negative Predictive Value (NPV). <b>Conclusions</b>: This system is designed to support clinical workflows by providing real-time, highly accurate second opinions, thereby reducing diagnostic errors and alleviating radiologist workload.