Scholarlink

Background <p>Radiographic bone age estimation is routinely performed in children to evaluate short stature, early or late puberty, and endocrine disorders, as well as for surgical planning.</p> Objective <p>To evaluate agreement between three state-of-the-art deep learning bone age estimation models and chronological age in a large contemporary pediatric cohort.</p> Materials and methods <p>We retrospectively identified a large contemporary cohort of children (<i>n</i>=7,189; 3,669 females and 3,520 males) aged 24–216&#xa0;months (mean 143.6±46.2&#xa0;months) with consecutive radiologically normal hand (including&#xa0;the&#xa0;wrist) radiographs that were evaluated for trauma between November 1, 2010, and October 31, 2020. Bone age was estimated according to Greulich and Pyle (GP)&#xa0;Atlas standards using three state-of-the-art deep learning models (Stanford&#xa0;University,&#xa0;Cincinnati Children's Hospital Medical Center (CCHMC) , and MedImageInsight models), each producing continuous bone age estimates in months. Mean and proportional bias relative to chronological age were assessed.</p> Results <p>All three models systematically overestimated chronological age, although the magnitude of bias varied by model and sex. The CCHMC model demonstrated the smallest overall mean bias (+3.20&#xa0;months), followed by the MedImageInsight (+4.60&#xa0;months) and Stanford (+7.03&#xa0;months) models. Mean differences compared with chronological age were statistically significant for all models (<i>P</i>&lt;0.0001). Evidence of proportional bias was observed in most models and subgroups. For all three models, the difference between predicted bone age and chronological age was greater for Black compared to White and Hispanic compared to non-Hispanic children.</p> Conclusion <p>GP Atlas–based bone age models systematically overestimate chronological age in a large contemporary cohort of children undergoing hand radiography for trauma, with biases related to age, sex, race, and ethnicity.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Agreement between three state-of-the-art deep learning bone age estimation models and chronological age in a large contemporary pediatric cohort

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月3日

查看全文
  • Elanchezhian Somasundaram,
  • Rama S. Ayyala,
  • William Tepe,
  • Bryan Luna,
  • Jonathan R. Dillman

摘要

Background

Radiographic bone age estimation is routinely performed in children to evaluate short stature, early or late puberty, and endocrine disorders, as well as for surgical planning.

Objective

To evaluate agreement between three state-of-the-art deep learning bone age estimation models and chronological age in a large contemporary pediatric cohort.

Materials and methods

We retrospectively identified a large contemporary cohort of children (n=7,189; 3,669 females and 3,520 males) aged 24–216 months (mean 143.6±46.2 months) with consecutive radiologically normal hand (including the wrist) radiographs that were evaluated for trauma between November 1, 2010, and October 31, 2020. Bone age was estimated according to Greulich and Pyle (GP) Atlas standards using three state-of-the-art deep learning models (Stanford University, Cincinnati Children's Hospital Medical Center (CCHMC) , and MedImageInsight models), each producing continuous bone age estimates in months. Mean and proportional bias relative to chronological age were assessed.

Results

All three models systematically overestimated chronological age, although the magnitude of bias varied by model and sex. The CCHMC model demonstrated the smallest overall mean bias (+3.20 months), followed by the MedImageInsight (+4.60 months) and Stanford (+7.03 months) models. Mean differences compared with chronological age were statistically significant for all models (P<0.0001). Evidence of proportional bias was observed in most models and subgroups. For all three models, the difference between predicted bone age and chronological age was greater for Black compared to White and Hispanic compared to non-Hispanic children.

Conclusion

GP Atlas–based bone age models systematically overestimate chronological age in a large contemporary cohort of children undergoing hand radiography for trauma, with biases related to age, sex, race, and ethnicity.