CT影像组学与机器学习术前预测肺腺癌STAS分级
本研究基于293例肺腺癌患者CT影像组学特征,构建机器学习模型预测经气腔播散(STAS)及其分级,并以92例外部数据验证。STAS以2500 µm为界分为I、II级,随机森林模型预测STAS存在的AUC为0.779–0.888。CT影像组学可无创预测STAS分级,辅助手术决策与预后评估。
要点
- STAS II级与肺腺癌无复发生存期独立相关(P=0.037),I级无此关联
- 随机森林模型检测STAS内部验证AUC达0.886–0.888,外部验证AUC为0.779
- 影像组学联合临床-影像特征模型预测STAS分级外部验证AUC为0.796
核心结论
- STAS分级可改善肺腺癌预后分层,STAS II级是较差无复发生存期的独立预测因素
- 基于CT影像组学的机器学习模型可无创预测STAS分级,辅助手术决策与预后判断
研究设计与样本
- 回顾性研究,293例肺腺癌患者用于训练与内部验证,92例来自国家肺筛查试验用于外部验证
- STAS定义为肿瘤边缘以外的肿瘤细胞,以2500 µm为阈值分为I级和II级
- 采用Cox回归分析STAS分级与无复发生存期的关系,采用最小冗余最大相关法筛选影像组学特征
- 11种机器学习分类器预测STAS存在及分级,逻辑回归构建临床-影像联合模型
诊断标准与关键数值
- STAS检测:随机森林模型训练/内部验证/外部验证AUC分别为0.888、0.886、0.779,准确率分别为81.5%、85.2%、69.6%
- STAS检测:联合模型训练/内部验证/外部验证AUC分别为0.877、0.894、0.802,准确率分别为77.6%、85.2%、72.8%
- STAS分级:逻辑回归模型AUC分别为0.845、0.852、0.798,准确率分别为78.2%、70.4%、77.1%
- STAS分级:联合模型AUC分别为0.845、0.855、0.796,准确率分别为78.2%、70.4%、77.1%
- STAS II级与较差无复发生存期独立相关(P=0.037),STAS I级无统计学意义
临床应用与阅片要点
- 随机森林影像组学模型检测STAS的内部验证AUC可达0.886,提示CT纹理特征对STAS预测有临床应用潜力
- 联合临床-影像特征与影像组学的模型外部验证AUC为0.796,用于STAS分级时可辅助术前风险分层
- STAS分级比单纯检出更有预后价值,报告中提示II级对临床手术范围决策有参考意义
局限性
- 回顾性研究设计,外部验证来自筛查试验人群,与临床患者人群可能存在差异
- 样本量有限,STAS分级模型外部验证AUC低于内部验证,泛化性有待更大样本检验
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: The distance of spread through air spaces (STAS) dissemination is associated with prognosis in lung adenocarcinoma (LUAD). This study aimed to develop a computed tomography (CT) radiomics-based machine learning model to predict STAS grade.
MATERIALS AND METHODS: Retrospective data included 293 LUAD patients for training/internal validation and 92 from the National Lung Screening Trial for external validation. STAS, defined as tumor cells beyond the tumor edge, was stratified by a 2500 µm threshold into grade I and II. Cox regression assessed associations between STAS grade and recurrence-free survival (RFS). Radiomics features were selected by minimum redundancy maximum relevance (MRMR), and 11 machine learning classifiers predicted STAS presence and grade. Independent clinic-radiological predictors were identified by univariable and multivariable analyses, and logistic regression combined these with the best radiomics model to build a combined model. Performance was evaluated by area under the curve (AUC) and accuracy (ACC).
RESULTS: STAS grade II was independently associated with poorer RFS (P = 0.037), while grade I was not. For STAS detection, the random forest model achieved AUCs of 0.888, 0.886 and 0.779 with accuracies of 81.5%, 85.2%, and 69.6%; the combined model performed similarly (AUCs 0.877, 0.894, 0.802; accuracies 77.6%, 85.2%, 72.8%). For STAS grading, logistic regression yielded AUCs of 0.845, 0.852, and 0.798 (accuracies 78.2%, 70.4%, 77.1%), with the combined model comparable (AUCs 0.845, 0.855, 0.796; accuracies 78.2%, 70.4%, 77.1%).
CONCLUSION: STAS grading improves prognostic stratification in LUAD. CT-based radiomics models allow noninvasive prediction of STAS grade, aiding surgical decisions and prognosis.
引用
- Chen, Qu, Chen, et al. Integrating CT Radiomics and Machine Learning for Preoperative Assessment of STAS Grading and Prognostic Stratification in Lung Adenocarcinoma. Acad Radiol. 2026. PMID: 42469041. doi:10.1016/j.acra.2026.06.057
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。