基于CT细胞外容积分数的可解释机器学习模型预测良恶性小肾脏肿块
这项回顾性分析纳入230例接受小肾脏肿块切除且有术前影像的患者(内部185例、外部45例),手动测量包括细胞外容积分数在内的11项多期增强CT参数并结合临床实验室数据。特征选择后构建多种机器学习分类器,含细胞外容积分数的极限梯度提升模型鉴别良恶性小肾脏肿块的AUC在内部训练集为0.993、内部验证集为0.986、外部测试集为0.951,SHAP分析证实细胞外容积分数贡献最大。
要点
- 含细胞外容积分数的极限梯度提升模型鉴别良恶性小肾脏肿块AUC:内部训练集0.993、内部验证集0.986、外部测试集0.951。
- SHAP分析显示细胞外容积分数是对小肾脏肿块定性贡献最大的特征。
- 多期增强CT的细胞外容积分数联合常规增强CT参数具有鉴别良恶性小肾脏肿块的诊断效能。
核心结论
- 多期增强CT衍生的细胞外容积分数与常规增强CT参数整合,在鉴别良恶性小肾脏肿块方面表现出诊断效能。
研究设计与样本
- 回顾性分析纳入230例接受小肾脏肿块切除且有术前影像的患者,其中内部185例、外部45例;内部队列分为训练集136例和验证集49例;组织病理学将病灶分类为肾细胞癌183例和良性肿块47例;手动测量包括细胞外容积分数在内的11项多期增强CT参数及临床和实验室数据;采用单因素分析和最小绝对收缩与选择算子正则化进行特征选择,据此构建多种机器学习分类器,用受试者工作特征曲线和分类检验评估性能,并用SHAP解释最优模型。
诊断标准与关键数值
- 含细胞外容积分数的极限梯度提升模型在鉴别恶性和良性小肾脏肿块时,曲线下面积在内部训练集为0.993、内部验证集为0.986、外部测试集为0.951。
临床应用与阅片要点
- 作者认为将多期增强CT衍生的细胞外容积分数与常规增强CT参数整合,在鉴别良恶性小肾脏肿块方面具有诊断效能,可支持个性化管理。
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
RATIONALE AND OBJECTIVES: We developed a machine learning model comprising morphological characteristics, enhancement dynamics, and extracellular volume (ECV) fractions for distinguishing malignant and benign small renal masses (SRMs), supporting personalised management.
MATERIALS AND METHODS: This retrospective analysis involved 230 patients who underwent SRM resection with preoperative imaging, including 185 internal and 45 external cases. The internal cohort was split into training (n=136) and validation (n=49) sets. Histopathological evaluation categorised the lesions as renal cell carcinomas (n=183) or benign masses (n=47). Eleven multiphasic contrast-enhanced computed tomography (CT) parameters, including the ECV fraction, were manually measured, along with clinical and laboratory data. Feature selection involved univariate analysis and least absolute shrinkage and selection operator regularisation. Feature selection informed various machine learning classifiers, and performance was evaluated using receiver operating characteristic curves and classification tests. The optimal model was interpreted using SHapley Additive exPlanations (SHAP).
RESULTS: The analysis included 183 carcinoma and 47 benign SRM cases. Feature selection identified seven discriminative parameters, including the ECV fraction, which informed multiple machine learning models. The Extreme Gradient Boosting model incorporating ECV exhibited optimal performance in distinguishing malignant and benign SRMs, achieving area under the curve values of 0.993 (internal training set), 0.986 (internal validation set), and 0.951 (external test set). SHAP analysis confirmed ECV as the top contributor to SRM characterisation.
CONCLUSION: The integration of multiphase contrast-enhanced CT-derived ECV fraction with conventional contrast-enhanced CT parameters demonstrated diagnostic efficacy in differentiating malignant and benign SRMs.
引用
- Guo Y, Fang Q, Li Y, et al. Prediction of Benign and Malignant Small Renal Masses Using CT-Derived Extracellular Volume Fraction: An Interpretable Machine Learning Model. Acad Radiol. 2025. PMID: 40784843. doi:10.1016/j.acra.2025.07.054
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。