人工智能在韩国儿童骨龄评估中的应用:以健康实足年龄与Greulich-Pyle年龄为标签训练的深度学习模型比较
研究基于21036张韩国儿童手部X线片,以实足年龄为标签训练卷积神经网络(Korean模型),并与以Greulich-Pyle年龄为标签的商业模型(GP-based模型)在两个外部数据集(Institution 1 n=343;Institution 2 n=321)上比较骨龄预测性能。Korean模型在Institution 1的RMSE(11.2 vs. 13.8个月,P=0.004)、MAE(8.2 vs. 10.5个月,P=0.002)及18个月内预测比例(88.3% vs. 82.2%,P=0.031)优于GP-based模型,在Institution 2的MAE(9.5 vs. 11.0个月,P=0.022)及6个月内预测比例(44.5% vs. 36.4%,P=0.044)更优。结论认为Korean模型在韩国儿童骨龄评估中表现更好,但需进一步验证。
要点
- Korean模型在Institution 1的MAE为8.2个月,低于GP-based模型的10.5个月(P=0.002)。
- Korean模型在Institution 2的6个月内预测比例为44.5%,高于GP-based模型的36.4%(P=0.044)。
- 两个模型在Institution 2的RMSE及18、24个月内预测比例无显著差异报告。
核心结论
- 以无已知影响骨发育疾病的韩国儿童实足年龄为标签训练的Korean模型,在韩国儿童骨龄评估中表现优于以Greulich-Pyle年龄为标签的GP-based模型;需进一步验证以确认其准确性。
研究设计与样本
- 研究使用1998至2019年间21036张无已知影响骨发育疾病的韩国儿童手部X线片(中位年龄9岁,IQR 7-12岁;男:女=11794:9242)及实足年龄标签训练卷积神经网络(Korean模型),并构建两个外部数据集(Institution 1 n=343,中位年龄10岁,IQR 4-15岁,男:女=183:160;Institution 2 n=321,中位年龄9岁,IQR 5-14岁,男:女=164:157)测试性能,与商业模型VUNO Med-BoneAge version 1.1(以Greulich-Pyle年龄为标签,GP-based模型)比较。
诊断标准与关键数值
- Institution 1:Korean模型RMSE 11.2个月 vs. GP-based模型13.8个月(P=0.004),MAE 8.2个月 vs. 10.5个月(P=0.002),骨龄预测在实足年龄18个月内的比例88.3% vs. 82.2%(P=0.031)。
- Institution 2:Korean模型MAE 9.5个月 vs. GP-based模型11.0个月(P=0.022),骨龄预测在实足年龄6个月内的比例44.5% vs. 36.4%(P=0.044)。
局限性
- 需进一步验证以确认其准确性。
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
OBJECTIVE: To develop a deep-learning-based bone age prediction model optimized for Korean children and adolescents and evaluate its feasibility by comparing it with a Greulich-Pyle-based deep-learning model.
MATERIALS AND METHODS: A convolutional neural network was trained to predict age according to the bone development shown on a hand radiograph (bone age) using 21036 hand radiographs of Korean children and adolescents without known bone development-affecting diseases/conditions obtained between 1998 and 2019 (median age [interquartile range {IQR}], 9 [7-12] years; male:female, 11794:9242) and their chronological ages as labels (Korean model). We constructed 2 separate external datasets consisting of Korean children and adolescents with healthy bone development (Institution 1: n = 343; median age [IQR], 10 [4-15] years; male: female, 183:160; Institution 2: n = 321; median age [IQR], 9 [5-14] years; male: female, 164:157) to test the model performance. The mean absolute error (MAE), root mean square error (RMSE), and proportions of bone age predictions within 6, 12, 18, and 24 months of the reference age (chronological age) were compared between the Korean model and a commercial model (VUNO Med-BoneAge version 1.1; VUNO) trained with Greulich-Pyle-based age as the label (GP-based model).
RESULTS: Compared with the GP-based model, the Korean model showed a lower RMSE (11.2 vs. 13.8 months; P = 0.004) and MAE (8.2 vs. 10.5 months; P = 0.002), a higher proportion of bone age predictions within 18 months of chronological age (88.3% vs. 82.2%; P = 0.031) for Institution 1, and a lower MAE (9.5 vs. 11.0 months; P = 0.022) and higher proportion of bone age predictions within 6 months (44.5% vs. 36.4%; P = 0.044) for Institution 2.
CONCLUSION: The Korean model trained using the chronological ages of Korean children and adolescents without known bone development-affecting diseases/conditions as labels performed better in bone age assessment than the GP-based model in the Korean pediatric population. Further validation is required to confirm its accuracy.
引用
- Kim PH, Yoon HM, Kim JR, et al. Bone Age Assessment Using Artificial Intelligence in Korean Pediatric Population: A Comparison of Deep-Learning Models Trained With Healthy Chronological and Greulich-Pyle Ages as Labels. Korean J Radiol. 2023. PMID: 37899524. doi:10.3348/kjr.2023.0092
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。