首个开源全自动骨龄评估系统，用AI精准识别20根手骨发育阶段。
BoneAgeTW2: Automated Skeletal Maturation Assessment via the Tanner-Whitehouse 2 Method, Deep Learning, and Clinical Report Generation with Distribution Curves
- 用YOLOv8检测20根手骨位置，EfficientNet-B3分类每根骨的发育阶段
- 基于12611张图像训练，可生成含分布曲线的临床报告
- 适合放射科医生、儿科医生快速辅助诊断骨龄异常
我们提出BoneAgeTW2，首个完全开源的端到端自动化系统，实现Tanner-Whitehouse 2（TW2）临床骨龄评估全流程。系统采用YOLOv8精确检测和定位放射影像中的20根TW2手骨，并使用EfficientNet-B3主干网络搭配20个独立分类头，同时为每根骨分配发育阶段（A-I）。基于预测结果，系统自动生成包含所有20根骨交互式高斯分布曲线的临床PDF报告，支持与人群标准直接对比。模型在公开的RSNA儿科骨龄挑战数据集（12,611张手部X光片）上训练，通过伪标签策略从全局骨龄标注中推导出每根骨的阶段标签。完整代码已公开于https://github.com/jmmana/BoneAgeTW2。
原文摘要 · Abstract (English)
We present BoneAgeTW2, the first fully open-source system to automate the complete Tanner-Whitehouse 2 (TW2) clinical protocol for skeletal maturity assessment end-to-end. The system employs YOLOv8 for precise detection and localization of the 20 TW2 hand bones from radiographic images, and an EfficientNet-B3 backbone with 20 independent classification heads to assign maturation stages (A-I) to each bone simultaneously. From these predictions, the system automatically generates clinical PDF reports including interactive Gaussian distribution curves for all 20 bones, enabling direct comparison with population norms. The model is trained on the public RSNA Pediatric Bone Age Challenge dataset (12,611 hand radiographs) using a pseudo-labeling strategy to derive per-bone stage labels from global bone age annotations. The full codebase is publicly available at https://github.com/jmmana/BoneAgeTW2.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。