文献速递乳腺MR

MRI影像组学联合临床数据预测70基因风险的多中心模型

Development and Validation of an Interpretable Model Integrating Radiomics and Clinical Data for Predicting 70-gene Signature Risk in Breast Cancer: A Multicenter Study.
PubMed 文献 · Acad Radiol · 2026-07-07

本研究回顾性纳入三个中心HR+/HER2-早期乳腺癌患者,分别构成训练队列80例及两个外部验证队列60例和62例,从多参数MRI提取影像组学特征并结合临床变量建模。多层感知机影像组学模型表现最佳,联合模型AUC在三个队列分别为0.860、0.764和0.792,优于单纯临床模型和单纯影像组学模型。SHAP分析显示Ki-67是影响最大的预测因素。

要点

  • 联合MRI影像组学与临床数据的模型预测70基因风险优于单一模型
  • Ki-67和年龄是关键临床预测因素,阅片时可重点关注相关病理信息
  • 多中心外部验证显示模型有一定泛化能力,但外部验证AUC较训练队列下降

核心结论

  • 联合MRI影像组学与临床数据的可解释机器学习模型在HR+/HER2-早期乳腺癌70基因风险分层中显示出有前景的预测效能,可作为非侵入性个体化风险评估工具

研究设计与样本

  • 回顾性多中心研究,三个医学中心分别构成训练队列80例、外部验证队列1为60例、外部验证队列2为62例
  • 从多参数MRI提取影像组学特征,评估八种机器学习分类器,选取最佳模型进行后续分析
  • 以70基因签名状态作为参考标准,构建影像组学-临床联合模型并以AUC和决策曲线分析评估

关键影像表现/征象

  • 从多参数MRI数据中最终筛选出四个影像组学特征用于模型构建
  • 多层感知机(MLP)在八种分类器中表现最佳,作为基础影像组学模型
  • SHAP分析显示Ki-67是模型中最具影响力的预测因素,年龄也为关键临床预测变量

诊断标准与关键数值

  • 联合模型在训练队列AUC为0.860,外部验证队列1为0.764,外部验证队列2为0.792
  • 单纯临床模型AUC为0.694、0.655、0.674,单纯影像组学模型AUC为0.773、0.674、0.681,联合模型优于两者
  • 决策曲线分析显示联合模型较单纯模型提供更好的临床净获益

临床应用与阅片要点

  • 对HR+/HER2-早期乳腺癌患者,可提取多参数MRI影像组学特征并结合Ki-67和年龄信息辅助评估70基因风险
  • 模型可作为70基因检测前的非侵入性预筛工具,减少不必要的基因检测成本
  • 注意外部验证队列AUC低于训练队列,实际应用中需结合本中心数据校准后使用

局限性

  • 回顾性研究设计存在选择偏倚可能
  • 外部验证队列AUC较训练队列明显下降,模型跨中心泛化能力有待进一步验证

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: The 70-gene signature (MammaPrint) guides risk assessment and treatment in the hormone receptor-positive/human epidermal growth factor receptor 2-negative (HR+/HER2-) early breast cancer but is limited by cost and laboratory requirements. This study aimed to develop and externally validate an interpretable MRI radiomics-clinical machine learning model to predict 70-gene signature status in patients with HR+/HER2- early-stage breast cancer.

MATERIALS AND METHODS: This study retrospectively enrolled patients with HR+/HER2- breast cancer from three medical centers, comprising a training cohort (n = 80 from center 1), external validation cohort 1 (n = 60 from center 2), and external validation cohort 2 (n = 62 from center 3). Radiomics features were derived from multiparametric MRI. A total of eight machine learning classifiers were assessed, with the best-performing model chosen for subsequent analysis. A radiomics-clinical model integrating radiomics and clinical variables was constructed and assessed using the area under the curve (AUC) and decision curve analysis (DCA), with interpretability evaluated by the Shapley Additive exPlanations (SHAP) method.

RESULTS: Age and Ki-67 emerged as key clinical predictors. From the multiparametric MRI data, four radiomics features were ultimately selected for model construction. Among classifiers, the multilayer perceptron (MLP)-based radiomics model performed best. The combined model integrating radiomics and clinical variables achieved AUCs of 0.860, 0.764, and 0.792 in the training cohort and two external validation cohorts, respectively, surpassing both the clinical model (AUCs: 0.694, 0.655, 0.674) and the best radiomics-only model (AUCs: 0.773, 0.674, 0.681). DCA demonstrated that the combined model yielded better clinical net benefit, and SHAP analysis identified Ki-67 as the most influential predictor.

CONCLUSION: The interpretable machine learning model integrating MRI radiomics with clinical data demonstrated promising performance in stratifying 70-gene signature risk in HR+/HER2- early-stage breast cancer, providing a potential noninvasive tool to support personalized risk assessment and guide treatment decisions.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Yang, Zhang, Xu, et al. Development and Validation of an Interpretable Model Integrating Radiomics and Clinical Data for Predicting 70-gene Signature Risk in Breast Cancer: A Multicenter Study. Acad Radiol. 2026. PMID: 42414134. doi:10.1016/j.acra.2026.06.003

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。