文献速递乳腺技术与安全US

基于双模态超声的像素级影像组学与深度学习预测乳腺癌Ki-67表达

Pixel-level Radiomics and Deep Learning for Predicting Ki-67 Expression in Breast Cancer Based on Dual-modal Ultrasound Images.
PubMed 文献 · Acad Radiol · 2026-01-14

本研究基于二维超声和应变弹性超声图像,开发并验证了一种整合像素级影像组学特征图、超声图像和临床指标的Vision-Mamba深度学习模型(V-MURC),用于预测乳腺癌Ki-67表达。多中心回顾性队列纳入1031例,另前瞻性纳入63例验证。内部验证、外部测试和前瞻性验证队列的AUC分别为0.954、0.941和0.945,模型显示出良好的区分度和校准度。

要点

  • V-MURC模型整合二维超声、应变弹性超声及临床指标,可术前无创预测乳腺癌Ki-67表达状态。
  • 模型在内部验证、外部测试和前瞻性验证中AUC均达0.94以上,区分度良好。
  • 联合模型性能显著优于单一模型,校准曲线和决策曲线支持其临床应用价值。

核心结论

  • 基于像素级影像组学特征图的V-MURC模型可准确预测乳腺癌Ki-67表达,可能成为临床个体化治疗决策的有用工具。

研究设计与样本

  • 多中心研究,训练队列616例,内部验证队列265例,外部测试队列150例,另前瞻性纳入63例进一步验证。
  • 使用的超声模态为二维超声和应变弹性超声,核心算法为Vision-Mamba深度学习模型结合像素级影像组学特征图。
  • 模型性能通过ROC曲线、校准曲线和决策曲线分析评估,并用SHAP方法增强可解释性。

诊断标准与关键数值

  • V-MURC模型在内部验证、外部测试和前瞻性验证队列的AUC分别为0.954(95%CI,0.929-0.975)、0.941(95%CI,0.903-0.975)和0.945(95%CI,0.883-0.989)。
  • V-MURC模型在所有数据集中均显著优于各单一模型(Delong检验,P<0.05)。
  • 联合模型纳入了独立临床预测因子,具体临床指标原文未详细列出。

临床应用与阅片要点

  • 该模型提示二维超声图像和应变弹性图像的像素级影像组学特征图可用于辅助术前预测乳腺癌Ki-67表达。
  • SHAP分析提供模型决策过程的可视化解释,有助于理解哪些超声特征和临床因素影响Ki-67预测。

局限性

  • 原文未报告具体局限性内容。

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: This study aimed to develop a deep learning model using a novel pixel-level radiomics approach based on two-dimensional (2D) and strain elastography (SE) ultrasound images to predict Ki-67 expression in breast cancer (BC).

METHODS: This multicenter study included 1031 BC patients, who were divided into training (n = 616), internal validation (n = 265), and external test (n = 150) cohorts. An additional 63 patients were prospectively enrolled for further validation. The deep learning model, termed Vision-Mamba, predicts Ki67 expression by integrating ultrasound (2D and SE) images with pixel-level radiomics feature maps (RFMs). A combined model was subsequently constructed by incorporating independent clinical predictors. Model performance was assessed using receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA). SHapley Additive exPlanations (SHAP) were applied to enhance interpretability.

RESULTS: We developed a Vision-Mamba-US-RFMs-Clinical (V-MURC) model that integrates ultrasound images, RFMs, and clinical data for accurate prediction of Ki-67 expression in BC. The area under the ROC curve (AUC) values for the internal validation, external test, and prospective validation cohorts were 0.954 (95% CI, 0.929 - 0.975), 0.941 (95% CI, 0.903 - 0.975), and 0.945 (95% CI, 0.883 - 0.989), respectively, demonstrating excellent discrimination and calibration. Compared with individual models, the V-MURC model achieved significantly superior performance across all datasets (Delong test, P < 0.05). Calibration curves and DCA further supported its clinical applicability. SHAP analysis provided visual interpretability of the model's decision-making process.

CONCLUSION: The V-MURC model based on pixel-level RFMs can accurately predict Ki-67 expression in BC and may serve as a valuable tool for individualized treatment decision-making in clinical practice.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Wei, Xia, Zhang, et al. Pixel-level Radiomics and Deep Learning for Predicting Ki-67 Expression in Breast Cancer Based on Dual-modal Ultrasound Images. Acad Radiol. 2026. PMID: 41539915. doi:10.1016/j.acra.2025.12.047

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。