文献速递神经MR

基于影像组学的可解释机器学习模型用于鉴别胶质母细胞瘤与单发脑转移瘤

Interpretable Machine Learning Models for Differentiating Glioblastoma From Solitary Brain Metastasis Using Radiomics.
PubMed 文献 · Acad Radiol · 2025-05-27

回顾性分析434例经组织病理学确诊的胶质母细胞瘤(226例)与单发脑转移瘤(208例)患者,基于增强T1加权MRI提取影像组学特征,采用最小冗余最大相关和最小绝对收缩与选择算子回归筛选特征,训练梯度提升和lightGBM等机器学习模型。验证组中GradientBoost分类器AUC最高为0.927,随机森林AUC为0.925;LGBM模型测试准确率最高为86.2%。高阶特征模型在所有指标上优于低阶特征模型,SHAP分析增强了模型可解释性。

要点

  • 验证组中GradientBoost鉴别胶质母细胞瘤与单发脑转移瘤的AUC为0.927
  • LGBM模型测试准确率最高为86.2%,敏感度0.911,阴性预测值0.895
  • 高阶特征模型在全部指标上均优于低阶特征模型

核心结论

  • 基于影像组学的机器学习技术可有效区分胶质母细胞瘤与单发脑转移瘤,基于梯度提升树的模型如LGBM表现更优,高阶特征显著提高模型准确性和鲁棒性,SHAP技术增强模型可解释性与透明度。

研究设计与样本

  • 回顾性分析434例经组织病理学确诊的患者,其中胶质母细胞瘤226例、单发脑转移瘤208例,基于增强T1加权MRI提取影像组学特征,经最小冗余最大相关和最小绝对收缩与选择算子回归筛选特征,训练GradientBoost和lightGBM等机器学习模型,并通过受试者工作特征分析和曲线下面积评估性能。

诊断标准与关键数值

  • 验证组GradientBoost分类器AUC为0.927,随机森林AUC为0.925,GradientBoost敏感度为0.911、阴性预测值为0.889;LGBM模型测试准确率为86.2%,敏感度为0.911,阴性预测值为0.895,阳性预测值为0.837。

临床应用与阅片要点

  • SHAP分析可量化每个特征对模型预测的影响,提供影像组学特征对分类决策贡献的直观可视化,有助于理解模型判别胶质母细胞瘤与单发脑转移瘤的依据。

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

PURPOSE: To develop and validate interpretable machine learning models for differentiating glioblastoma (GB) from solitary brain metastasis (SBM) using radiomics features from contrast-enhanced T1-weighted MRI (CE-T1WI), and to compare the impact of low-order and high-order features on model performance.

METHODS: A cohort of 434 patients with histopathologically confirmed GB (226 patients) and SBM (208 patients) was retrospectively analyzed. Radiomic features were derived from CE-T1WI, with feature selection conducted through minimum redundancy maximum relevance and least absolute shrinkage and selection operator regression. Machine learning models, including GradientBoost and lightGBM (LGBM), were trained using low-order and high-order features. The performance of the models was assessed through receiver operating characteristic analysis and computation of the area under the curve, along with other indicators, including accuracy, specificity, and sensitivity. SHapley Additive Explanations (SHAP) analysis is used to measure the influence of each feature on the model's predictions.

RESULTS: The performances of various machine learning models on both the training and validation datasets were notably different. For the training group, the LGBM, CatBoost, multilayer perceptron (MLP), and GradientBoost models achieved the highest AUC scores, all exceeding 0.9, demonstrating strong discriminative power. The LGBM model exhibited the best stability, with a minimal AUC difference of only 0.005 between the training and test sets, suggesting strong generalizability. Among the validation group results, the GradientBoost classifier achieved the maximum AUC of 0.927, closely followed by random forest at 0.925. GradientBoost also demonstrated high sensitivity (0.911) and negative predictive value (NPV, 0.889), effectively identifying true positives. The LGBM model showed the highest test accuracy (86.2%) and performed excellently in terms of sensitivity (0.911), NPV (0.895), and positive predictive value (PPV, 0.837). The models utilizing high-order features outperformed those based on low-order features in all the metrics. SHAP analysis further enhances model interpretability, providing insights into feature importance and contributions to classification decisions.

CONCLUSION: Machine learning techniques based on radiomics can effectively distinguish GB from SBM, with gradient boosting tree-based models such as LGBMs demonstrating superior performance. High-order features significantly improve model accuracy and robustness. SHAP technology enhances the interpretability and transparency of models for distinguishing brain tumors, providing intuitive visualization of the contribution of radiomic features to classification.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Xia X, Wu W, Tan Q, et al. Interpretable Machine Learning Models for Differentiating Glioblastoma From Solitary Brain Metastasis Using Radiomics. Acad Radiol. 2025. PMID: 40436711. doi:10.1016/j.acra.2025.05.016

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。