文献速递头颈技术与安全US

基于多模态超声机器学习模型与SHAP可解释性鉴别良恶性颈部淋巴结

Differentiation of Benign and Malignant Cervical Lymph Nodes Using a Multi-Modal Ultrasound-Based Machine Learning Model With SHAP Interpretability.
PubMed 文献 · J Ultrasound Med · 2026-03-05

回顾性纳入190例疑似颈部淋巴结病变患者,采集临床与二维超声、CDFI、MVFI、CEUS多模态特征,构建10种机器学习模型;梯度提升机模型在测试集AUC 0.987、准确率0.929、敏感度0.879、特异度0.965、F1 0.935,显著优于经验丰富的超声医师(AUC 0.904,p=.03);SHAP提示CEUS增强模式、L/S比、年龄、PI、VI为最重要特征。

要点

  • 梯度提升机模型测试集AUC 0.987,显著优于经验丰富超声医师的AUC 0.904(p=.03)。
  • SHAP显示最重要预测特征为CEUS增强模式、L/S比、年龄、PI与VI。
  • 恶性淋巴结常见组合:CEUS向心性不均匀增强、L/S<2、高回声灶、MVFI混合型血流、VI升高。

核心结论

  • 基于多模态超声特征的梯度提升机模型能准确鉴别良恶性颈部淋巴结,SHAP提供透明可视化的模型决策解释,支持其作为临床决策可靠工具的潜力。

研究设计与样本

  • 回顾性研究,纳入2022年8月至2025年1月在哈尔滨医科大学附属第四医院获得病理结果的190例疑似颈部淋巴结病变患者,均行二维超声、CDFI、MVFI与CEUS,采集临床数据与多模态超声特征,开发并比较10种机器学习算法。

关键影像表现/征象

  • 单因素分析确定18个与恶性显著相关的特征,包括年龄、短轴、L/S比、形态、皮质厚度、皮质回声、钙化、囊性变、高回声灶、网状/条索状回声、淋巴门可见性、CDFI血管模式、搏动指数、MVFI血管模式、血管指数、CEUS增强模式、增强均匀性、坏死区。
  • 病例分析显示恶性淋巴结常与CEUS向心性不均匀增强、L/S<2、高回声灶、MVFI混合型血流及VI升高组合相关。

诊断标准与关键数值

  • 梯度提升机模型在测试集上AUC 0.987(95%CI:0.967-1.000)、准确率0.929、敏感度0.879、特异度0.965、F1分数0.935。
  • 梯度提升机模型AUC 0.987显著优于经验丰富超声医师的AUC 0.904(p=.03)。
  • SHAP解释显示对预测影响最大的特征为CEUS增强模式、L/S比、年龄、PI与VI。

临床应用与阅片要点

  • 阅片时可关注CEUS增强模式、L/S比、年龄、PI与VI等SHAP提示的高权重特征。
  • 恶性淋巴结常表现为CEUS向心性不均匀增强、L/S<2、高回声灶、MVFI混合型血流及VI升高的组合。
  • 模型基于二维超声、CDFI、MVFI与CEUS多模态特征,可作为辅助鉴别良恶性的参考。

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

OBJECTIVES: To evaluate the diagnostic value of a machine learning (ML) model based on multi-modal ultrasound features in differentiating benign from malignant cervical lymph nodes, and to provide a visual interpretation of model decisions using shapley additive explanations (SHAP).

METHODS: This retrospective study included 190 patients with suspected cervical lymph node lesions who obtained a pathological result at the Fourth Affiliated Hospital of Harbin Medical University between August 2022 and January 2025. All patients underwent 2D ultrasound, color Doppler flow imaging (CDFI), microvascular flow imaging (MVFI), and contrast-enhanced ultrasound (CEUS). Clinical data (age and sex) and multi-modal ultrasound features were collected. Univariate analysis was used to identify variables significantly associated with lymph node malignancy. Ten ML algorithms were developed and compared to construct predictive models. Model performance was evaluated using multiple metrics such as the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, and F1 score. The SHAP framework was applied to interpret the decision-making process of the optimal model.

RESULTS: Univariate analysis identified 18 features significantly associated with malignancy, including age, short axis, L/S ratio, morphology, cortical thickness, cortical echogenicity, calcification, cystic change, hyperechoic foci, reticular/cord-like echogenicity, hilum visibility, CDFI vascular pattern, pulsatility index (PI), MVFI vascular pattern, vascularity index (VI), CEUS enhancement pattern, enhancement uniformity, and necrotic regions. Among the 10 ML algorithms, the gradient boosting machine (GBM) model achieved the best diagnostic performance, with an AUC of 0.987 (95% CI: 0.967-1.000), accuracy of 0.929, sensitivity of 0.879, specificity of 0.965, and F1 score of 0.935 on the test set. The GBM model significantly outperformed an experienced ultrasound physician (AUC = 0.904, p = .03). SHAP interpretation revealed that the most influential features for prediction included CEUS enhancement pattern, L/S ratio, age, PI, and VI. The case-based analysis further demonstrated that malignant lymph nodes were commonly associated with a combination of centripetal heterogeneous enhancement on CEUS, L/S <2, presence of hyperechoic foci, mixed-type vascularity on MVFI, and elevated VI values.

CONCLUSION: The GBM model based on multi-modal ultrasound features enables accurate differentiation between benign and malignant cervical lymph nodes. SHAP provides a transparent, visual interpretation of model decisions, demonstrating a novel methodological framework that integrates multi-modal data with explainable AI, supporting its potential as a reliable tool for clinical decision-making.

来源:J Ultrasound Med,查看原文。版权归原作者所有。

引用

  1. Gao M, Guo Y, Tian X, et al. Differentiation of Benign and Malignant Cervical Lymph Nodes Using a Multi-Modal Ultrasound-Based Machine Learning Model With SHAP Interpretability. J Ultrasound Med. 2026. PMID: 41784164. doi:10.1002/jum.70223

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。