Abstract
Tibial plateau fractures account for approximately 1% of skeletal fractures, with treatment strategies varying based on fracture type, displacement, and articular involvement. Diagnosis is labor-intensive, time-consuming, repetitive, and subject to considerable inter-observer variability. Automated and precise approaches could improve accuracy and efficiency in fracture severity classification. With advances in artificial intelligence (AI), especially deep learning, such techniques are increasingly applied in medicine, yet their performance depends on high-quality training data. Here, we present a first-of-its-kind open-access dataset for AI-based analysis of tibial plateau fractures. The dataset comprises 421 heterogeneous anterior-posterior radiographs from 186 patients (mean age 45.88 ± 17.54 years; 37 females, 149 males), including normal and fractured knees. Fractures were classified by expert orthopedic surgeons and radiologists using the Schatzker system: type I (14.51%), II (18.27%), III (6.45%), IV (5.91%), V (6.45%), VI (17.20%), and normal (31.18%). All images were segmented to generate tibial bone masks, supporting morphological analysis, AI training, and automated fracture assessment. This dataset facilitates AI-driven fracture detection, classification, preoperative planning, and orthopedic assistant education.