18F-Pentixafor PET/CT 机器学习预测原发性醛固酮增多症 CYP11B2 亚型
本研究纳入 89 例原发性醛固酮增多症或非功能性肾上腺腺瘤患者,基于 18F-Pentixafor PET/CT 影像组学与深度学习特征构建机器学习模型。联合模型在测试集中 AUC 达 0.907,敏感度为 1.000,F1 分数为 0.923,显著优于单一模型。该模型可无创预测经 CYP11B2 免疫组化确认的病理亚型。
要点
- 联合临床、影像组学与深度学习特征的模型预测 PA 亚型效能最佳,AUC 0.907。
- SHAP 分析提示病灶/肾上腺比值与 SUVmax 是与 CXCR4 表达相关的关键特征。
- 无创预测 CYP11B2 亚型有望减少肾上腺静脉取血依赖,辅助手术决策。
核心结论
- 可解释机器学习模型能无创预测经 CYP11B2 免疫组化确认的原发性醛固酮增多症病理亚型。
- 联合模型测试集 AUC 为 0.907,敏感度为 1.000,F1 分数为 0.923。
- 该方法可能减少对肾上腺静脉取血的依赖,有助于个体化手术决策。
研究设计与样本
- 单中心回顾性研究,纳入 2024 年 2 月至 2025 年 5 月间 89 例接受 18F-Pentixafor PET/CT 的 PA 或非功能性肾上腺腺瘤患者。
- 采用最小冗余最大相关与基于赤池信息准则的逐步回归进行两阶段特征选择。
- 使用支持向量机构建四种模型,以分层五折交叉验证优化超参数。
关键影像表现/征象
- SHAP 分析显示病灶/肾上腺比值与最大标准化摄取值在模型中贡献突出。
- 所筛选的 PET/CT 影像组学及深度学习特征与 CXCR4 和 CYP11B2 表达具有生物学对应关系。
诊断标准与关键数值
- 联合模型测试集 AUC 为 0.907,敏感度为 1.000,F1 分数为 0.923。
- 联合模型显著优于单独临床模型、影像组学模型和深度学习模型,p<0.01。
- 参考标准为 CYP11B2 免疫组化确认的手术病理亚型。
临床应用与阅片要点
- PET/CT 报告中可关注病灶/肾上腺比值与 SUVmax,二者为模型关键预测特征。
- 模型输出可辅助判断是否为 CYP11B2 定义的 PA 病理亚型,指导后续手术决策。
- 注意该模型基于单中心数据,外推到其他扫描参数或人群前需验证。
局限性
- 单中心回顾性设计,样本量 89 例,结果需多中心前瞻性研究验证。
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: This study aims to develop and validate an interpretable machine learning model that integrates clinical data, radiomics, and deep learning (DL) features extracted from 18F-AlF-NOTA-Pentixafor positron emission tomography/computed tomography (PET/CT) images for the non-invasive prediction of pathological subtypes in primary aldosteronism (PA).
METHODS: In this single-center retrospective study, we included 89 patients diagnosed with PA or non-functioning adrenal adenomas who underwent 18F-Pentixafor PET/CT between February 2024 and May 2025. Predictive models were built by integrating clinical data, PET/CT radiomics, and DL features. A two-stage feature selection strategy was employed, which utilized the minimum redundancy maximum relevance method followed by stepwise regression based on the Akaike information criterion. Four distinct models were constructed using the support vector machine algorithm, and their hyperparameters were optimized via stratified five-fold cross-validation. Model performance was rigorously evaluated by the area under the receiver operating characteristic curve (AUC), calibration analysis, and decision curve analysis. Furthermore, model interpretability was achieved using Shapley Additive Explanations (SHAP) to elucidate feature contributions.
RESULTS: The combined model demonstrated superior diagnostic accuracy in the test set, with an AUC of 0.907, perfect sensitivity (1.000), and an F1-score of 0.923. It significantly outperformed the clinical, radiomics, DL models individually (p<0.01). SHAP analysis identified lesion-to-adrenal ratio, maximum standardized uptake value, and selected PET/CT radiomics and DL features as key contributors, revealing biological alignment with CXCR4 and CYP11B2 expression.
CONCLUSION: An interpretable machine learning model can non-invasively predict surgically confirmed PA subtypes, defined by immunohistochemistry for CYP11B2. This approach may reduce the reliance on invasive adrenal vein sampling and facilitate personalized surgical decision-making.
引用
- Zhao, Chen, Duan, et al. Non-invasive Prediction of CYP11B2-Defined Subtypes in Primary Aldosteronism Using 18F-Pentixafor PET/CT and Machine Learning. Acad Radiol. 2026. PMID: 41530023. doi:10.1016/j.acra.2025.12.026
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。