PediURF, A Comprehensive X-ray Dataset for The Pediatric Ulna and Radius Fractures Analysis

Pediatric foream fractures, particularly involving the ulna and radius, are among the most common childhood injuries. However, the lack of standardized and openly available datasets has limited progress in artificial intelligence research and constrained clinical validation. To address this issue, we present the Pediatric Ulna and Radius Fractures (PediURF) dataset, which was collected with detailed annotations by expert radiologists across proximal, midshaft, and distal fracture types. By releasing PediURF, we aim to provide an accessible resource for algorithm development, benchmarking, and clinical training. To validate its utility, we developed URFNet, a dual-view classification model designed to integrate anteroposterior and lateral perspectives. Compared with other baseline models, the proposed model achieved the best performance. Therefore, this work provides a valuable foundation for future deep learning-based studies in pediatric fracture classification.儿童前臂骨折，尤其是累及尺骨与桡骨的骨折，是儿童最常见的创伤类型之一。然而，目前缺乏标准化且可公开获取的数据集，这不仅制约了人工智能相关研究的进展，也限制了临床验证工作的开展。为解决这一问题，本研究提出儿科尺桡骨骨折（Pediatric Ulna and Radius Fractures, PediURF）数据集，该数据集由专业放射科医师针对近端、骨干中段及远端三类骨折类型进行了详细标注并采集。本研究发布该数据集的初衷，是为算法开发、模型基准测试以及临床培训提供一个可便捷获取的研究资源。为验证该数据集的实用价值，本研究构建了URFNet模型——一种旨在整合前后位与侧位影像视角的双视图分类模型。与其他基线模型相比，本研究提出的URFNet模型取得了最优性能。因此，本研究为未来基于深度学习的儿科骨折分类相关研究提供了极具价值的研究基础。