文献速递儿科影像骨肌DR

利用深度学习估计儿童意外骨折的受伤时间

Using deep learning for estimation of time-since-injury in pediatric accidental fractures.
PubMed 文献 · Pediatr Radiol · 2025-04-22

本研究利用2000—2016年一所大型中西部儿童医院收治的6岁以下儿童意外长骨骨折X线片,训练并验证深度学习模型,对骨折图像进行年龄分组分类并直接估计受伤时间。模型在骨折年龄分类和估计上均优于基线,最佳模型估计任意长骨骨折年龄的平均绝对误差为6.2天,68%的估计值落在正确骨折年龄7天以内。

要点

  • 深度学习模型可对儿童意外长骨骨折X线片估计受伤时间,最佳模型平均绝对误差6.2天。
  • 最佳模型68%的估计值落在正确骨折年龄7天以内。
  • 模型在全部骨骼及特定骨类型上训练/验证时,骨折年龄分类与估计均优于基线。

核心结论

  • 深度学习模型能以优于基线的准确度估计儿童意外长骨骨折的受伤时间。

研究设计与样本

  • 二次数据分析,使用2000—2016年一所大型中西部儿童医院收治的6岁以下儿童意外长骨骨折X线片,共纳入399例患者的2328张X线片,采用交叉验证评估模型性能。

诊断标准与关键数值

  • 骨折年龄分类采用混淆矩阵、敏感度/特异度及激活图评估;骨折年龄估计采用平均绝对误差(MAE)和均方根误差(RMSE)评估;最佳模型估计任意长骨骨折年龄的MAE为6.2天,68%的估计值落在正确骨折年龄7天以内。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

BACKGROUND: Estimating time-since-injury of healing fractures is imprecise, encompassing excessively wide timeframes. Most injured children are evaluated at non-children's hospitals, yet pediatric radiologists can disagree with up to one in six skeletal imaging interpretations from referring community hospitals. There is a need to improve image interpretation by considering additional methods for fracture dating.

OBJECTIVE: To train and validate deep learning models to correctly estimate the age of pediatric accidental long bone fractures.

MATERIALS AND METHODS: This secondary data analysis used radiographic images of accidental long bone fractures in children <6 years at the time of injury seen at a large Midwestern children's hospital between 2000-2016. We built deep learning models both to classify fracture images into different age groups and to directly estimate fracture age (time-since-injury). We used cross-validation to evaluate model performance across various metrics, including confusion matrices, sensitivity/specificity, and activation maps for age classification, and mean absolute error (MAE) and root mean squared error (RMSE) for age estimation.

RESULTS: Our study cohort contained 2,328 radiographs from 399 patients. Overall, our models performed above baselines for fracture age classification and estimation, both when trained/validated across all bones and on specific bone types. The best model was able to estimate fracture age for any long bone with a MAE of 6.2 days and with 68% of estimates falling within 7 days of the correct fracture age.

CONCLUSION: Our study successfully demonstrated that, for radiographic dating of accidental fractures of long bones, deep learning models can estimate time-since-injury with above-baseline accuracy.

来源:Pediatr Radiol,查看原文。版权归原作者所有。

引用

  1. Brink FW, Adler B, Bambach S, et al. Using deep learning for estimation of time-since-injury in pediatric accidental fractures. Pediatr Radiol. 2025. PMID: 40258953. doi:10.1007/s00247-025-06223-4

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。