文献速递儿科影像神经MR

基于垂体MRI的可解释影像组学模型预测矮小症儿童生长激素缺乏:一项多中心研究

An Interpretable Radiomics Model Based on Pituitary MRI to Predict Growth Hormone Deficiency in Short-statured Children: A Multicenter Study.
PubMed 文献 · Acad Radiol · 2025-10-27

这项回顾性多中心研究纳入机构I的202例儿童(105例GHD、97例ISS)作为内部队列并按7:3分为训练/测试集,另纳入机构II和III的138例儿童(61例GHD、77例ISS)作为外部验证队列,从垂体MRI提取影像组学特征并构建六种机器学习模型。基于支持向量机(SVM)的影像组学模型诊断性能最高,训练、测试和外部验证队列AUC分别为0.877、0.878和0.885,SVM联合临床-影像组学模型效能相当(AUC分别为0.874、0.878和0.889),两种影像组学模型均显著优于临床模型(均p<0.001),而影像组学模型与临床-影像组学模型之间无统计学显著差异(均p>0.05)。SHAP分析识别出三个在GHD与ISS组间有显著差异的关键影像组学特征(均p<0.001)。

要点

  • 基于垂体MRI的SVM影像组学模型在外部验证队列预测GHD的AUC为0.885(95%CI: 0.833, 0.937)。
  • SVM影像组学模型与临床-影像组学模型诊断效能无统计学显著差异(均p>0.05),两者均显著优于临床模型(均p<0.001)。
  • SHAP分析识别出三个在GHD与ISS组间有显著差异的关键影像组学特征(均p<0.001)。

核心结论

  • 基于垂体MRI的可解释SVM影像组学模型能有效预测生长激素水平,为矮小症儿童提供了一种临床可行的无创替代生长激素激发试验的方法。

研究设计与样本

  • 回顾性多中心研究,内部队列来自机构I共202例儿童(105例GHD、97例ISS),按7:3比例分为训练集和测试集;外部验证队列来自机构II和机构III共138例儿童(61例GHD、77例ISS);基于垂体MRI提取影像组学特征,采用SelectKBest和LASSO筛选特征后构建六种机器学习模型,以AUC、敏感度、特异度和校准曲线评估诊断性能,并以SHAP评估模型可解释性。

诊断标准与关键数值

  • SVM影像组学模型在训练队列AUC为0.877(95%CI: 0.813, 0.928),测试队列AUC为0.878(95%CI: 0.786, 0.951),外部验证队列AUC为0.885(95%CI: 0.833, 0.937)。
  • SVM联合临床-影像组学模型在训练队列AUC为0.874(95%CI: 0.812, 0.928),测试队列AUC为0.878(95%CI: 0.786, 0.952),外部验证队列AUC为0.889(95%CI: 0.830, 0.939)。
  • 影像组学模型与临床-影像组学模型均显著优于临床模型(均p<0.001),而影像组学模型与临床-影像组学模型之间无统计学显著差异(均p>0.05)。
  • 共筛选出17个影像组学特征,SHAP分析识别出三个在GHD与ISS组间有显著差异的关键影像组学特征(均p<0.001)。

临床应用与阅片要点

  • 作者认为该可解释SVM影像组学模型可作为矮小症儿童生长激素激发试验的临床可行无创替代方法。

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

RATIONALE AND OBJECTIVES: To develop and validate an interpretable radiomics model based on pituitary MRI to predict growth hormone deficiency (GHD) in children with short stature.

METHODS: This retrospective multicenter study enrolled 202 children (105 GHD, 97 idiopathic short stature [ISS]) as an internal cohort (7:3 ratio for training/testing cohorts) from institution I, and 138 children (61 GHD, 77 ISS) from institution II and institution III as an external validation cohort. Radiomics features were selected by SelectKBest and least absolute shrinkage and selection operator (LASSO), subsequently used to construct six machine learning models. Diagnostic performance of model was evaluated by the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and calibration curves. The interpretability of the model was assessed using Shapley additive explanations (SHAP).

RESULTS: A total of 17 radiomics features were selected. Among all classifiers, support vector machine (SVM)-based radiomics model exhibited the highest diagnostic performance, with AUCs of 0.877 (95% CI: 0.813, 0.928), 0.878 (95% CI: 0.786, 0.951), and 0.885 (95% CI: 0.833, 0.937) in training, testing, and external validation cohorts, respectively. The SVM-integrated clinical-radiomics model yielded comparable efficacy, with AUCs of 0.874 (95% CI: 0.812, 0.928), 0.878 (95% CI: 0.786, 0.952), and 0.889 (95% CI: 0.830, 0.939) across the same cohorts. Both radiomics-based models significantly outperformed the clinical model (all p<0.001), while no statistically significant difference was observed between the radiomics and clinical-radiomics models (all p>0.05). The SHAP analysis identified three key radiomics features with significant differences between GHD and ISS groups (all p<0.001).

CONCLUSIONS: The interpretable radiomics-driven SVM model effectively predicts GH levels, providing a clinically viable, non-invasive alternative to GH stimulation test in children with short stature.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Shi F, Ren X, Xu Q, et al. An Interpretable Radiomics Model Based on Pituitary MRI to Predict Growth Hormone Deficiency in Short-statured Children: A Multicenter Study. Acad Radiol. 2025. PMID: 41152101. doi:10.1016/j.acra.2025.10.006

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。