文献速递头颈胸部CT

基于增强CT的多模态机器学习模型用于头颈部腺样囊性癌肺转移预测

Application of contrast-enhanced CT-driven multimodal machine learning models for pulmonary metastasis prediction in head and neck adenoid cystic carcinoma.
PubMed 文献 · Eur J Radiol · 2025-08-22

本研究回顾性分析130例病理确诊头颈部腺样囊性癌患者的增强CT影像与临床资料,按7:3随机分为训练集与测试集,提取影像组学与深度学习特征并经多特征融合后以LASSO回归筛选7个预测特征,采用9种机器学习算法构建肺转移预测模型。测试集中KNN、SVM、rpart、GBM、NB、GLM、LDA的AUC分别为0.687、0.863、0.737、0.793、0.763、0.867、0.844,rf与ada明显过拟合,GBM与GLM稳定性较高。作者认为基于增强CT的影像组学与深度学习方法可为头颈部腺样囊性癌肺转移预测提供有效辅助工具。

要点

  • 测试集中GLM与GBM预测头颈部腺样囊性癌肺转移的AUC分别为0.867与0.844,稳定性较高。
  • SVM、LDA、NB、rpart测试集AUC分别为0.863、0.844、0.763、0.737。
  • KNN测试集AUC为0.687;rf与ada出现明显过拟合。

核心结论

  • 基于增强CT的影像组学与深度学习方法可为头颈部腺样囊性癌患者肺转移预测提供有效辅助工具,显示出临床应用的潜在前景。

研究设计与样本

  • 回顾性分析130例病理确诊头颈部腺样囊性癌患者的增强CT影像数据与临床记录,按7:3随机分为训练集与测试集。
  • 提取影像组学特征与深度学习衍生特征并进行多特征融合,对训练集与测试集行Z分数归一化,经假设检验筛选显著特征后以LASSO回归(5折交叉验证)确定7个预测特征。
  • 采用ada、KNN、rf、NB、GLM、LDA、rpart、SVM-RBF、GBM共9种机器学习算法构建肺转移预测模型,用训练集训练、测试集测试。
  • 模型性能以召回率、敏感度、PPV、F1分数、精确率、患病率、NPV、特异度、准确率、检出率、检出患病率、平衡准确率等指标评价。

诊断标准与关键数值

  • 测试集中KNN、SVM、rpart、GBM、NB、GLM、LDA预测头颈部腺样囊性癌肺转移的AUC分别为0.687、0.863、0.737、0.793、0.763、0.867、0.844。
  • rf与ada模型出现明显过拟合。

临床应用与阅片要点

  • 作者认为基于增强CT影像组学与深度学习的多模态机器学习模型可作为预测头颈部腺样囊性癌肺转移的辅助工具。
  • 在所用算法中,GBM与GLM预测头颈部腺样囊性癌肺转移的稳定性较高。

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

OBJECTIVE: This study explores radiomics and deep learning for predicting pulmonary metastasis in head and neck Adenoid Cystic Carcinoma (ACC), assessing machine learning(ML) algorithms' model performance.

METHODS: The study retrospectively analyzed contrast-enhanced CT imaging data and clinical records from 130 patients with pathologically confirmed ACC in the head and neck region. The dataset was randomly split into training and test sets at a 7:3 ratio. Radiomic features and deep learning-derived features were extracted and subsequently integrated through multi-feature fusion. Z-score normalization was applied to training and test sets. Hypothesis testing selected significant features, followed by LASSO regression (5-fold CV) identifying 7 predictive features. Nine machine learning algorithms were employed to build predictive models for ACC pulmonary metastasis: ada, KNN, rf, NB, GLM, LDA, rpart, SVM-RBF, and GBM. Models were trained using the training set and tested on the test set. Model performance was evaluated using metrics such as recall, sensitivity, PPV, F1-score, precision, prevalence, NPV, specificity, accuracy, detection rate, detection prevalence, and balanced accuracy.

RESULTS: Machine learning models based on multi-feature fusion of enhanced CT, utilizing KNN, SVM, rpart, GBM, NB, GLM, and LDA, demonstrated AUC values in the test set of 0.687, 0.863, 0.737, 0.793, 0.763, 0.867, and 0.844, respectively. Rf and ada showed significant overfitting. Among these, GBM and GLM showed higher stability in predicting pulmonary metastasis of head and neck ACC.

CONCLUSION: Radiomics and deep learning methods based on enhanced CT imaging can provide effective auxiliary tools for predicting pulmonary metastasis in head and neck ACC patients, showing promising potential for clinical application.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Gong W, Cui Q, Fu S, et al. Application of contrast-enhanced CT-driven multimodal machine learning models for pulmonary metastasis prediction in head and neck adenoid cystic carcinoma. Eur J Radiol. 2025. PMID: 40857998. doi:10.1016/j.ejrad.2025.112377

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。