文献速递腹部胸部CT

机器学习CT影像组学识别肝癌高危食管静脉曲张出血

Machine learning-based CT radiomics for identifying high risk esophageal varices of bleeding in hepatocellular carcinoma.
PubMed 文献 · Abdom Radiol (NY) · 2026-10-20

本研究纳入151例肝细胞癌患者,基于增强CT提取曲张静脉特异性影像组学特征,以胃镜下高危征象或活动性出血为终点,建立机器学习模型。训练队列交叉验证AUC为0.956,时间验证队列AUC为0.926,敏感度93.1%,特异度71.4%。模型可为肝癌患者食管静脉曲张出血提供无创风险分层。

要点

  • 增强CT曲张静脉影像组学模型对高危食管静脉曲张有较高敏感度,可用于筛查。
  • 训练与时间验证AUC均较高,但特异度相对有限,不能完全替代胃镜。
  • 影像组学特征Surface-to-Volume Ratio与NGTDM Coarseness具有可行性。

核心结论

  • 基于增强CT的曲张静脉特异性影像组学模型对肝细胞癌患者高危食管静脉曲张出血具有高度敏感且数学稳定的无创风险分层能力。
  • 模型在独立时间验证队列中保持较高泛化能力,AUC为0.926。

研究设计与样本

  • 研究类型为回顾性研究,共纳入151例肝细胞癌患者。
  • 影像组学特征提取自胃镜检查前6个月内获得的增强CT图像。

关键影像表现/征象

  • 以胃镜下活动性出血或具有高危特征的曲张静脉作为终点。
  • Surface-to-Volume Ratio与NGTDM Coarseness为可行的影像组学特征。

诊断标准与关键数值

  • 训练队列中,经LASSO开发的曲张静脉特异性影像组学标签交叉验证AUC为0.956,95% CI 0.872-1.000。
  • 时间验证队列中,模型AUC为0.926,95% CI 0.846-0.984。
  • 时间验证队列中,模型敏感度为93.1%,特异度为71.4%。
  • 时间验证队列中,Brier评分为0.1186,校准截距为-0.157,校准斜率为1.354。

临床应用与阅片要点

  • 肝硬化合并肝细胞癌患者行增强CT时,可评估食管曲张静脉影像组学特征以辅助判断出血风险。
  • 该模型敏感度高,适合用于筛查高危患者,减少不必要的胃镜检查。
  • 特异度有限,模型判断为低危时仍需结合临床综合判断。

局限性

  • 研究为单中心回顾性设计,未报告外部多中心验证。
  • 训练与时间验证队列中高危病例比例均较高,可能影响模型在低患病率人群中的表现。

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: Esophageal variceal (EV) bleeding is a lethal complication in patients with hepatocellular carcinoma (HCC). Current risk stratification relies on invasive endoscopy or systemic surrogates of liver cirrhosis. This study aimed to develop a machine learning model utilizing EV-specific CT radiomics to identify high-risk esophageal varices, as defined by endoscopic criteria, in patients with HCC.

METHODS: 151 HCC patients were enrolled and divided into a training cohort (n = 101; 75 high-risk; January 2017 - December 2022) and an independent temporal validation cohort (n = 50; 29 high-risk; January 2023 - December 2024). Endoscopic stigmata were used as an endpoint, including active bleeding or varices with high-risk features. Radiomic features were extracted from contrast-enhanced CT images acquired within six months prior to endoscopy. Model performance was evaluated using the area under the curve (AUC) of receiver operating characteristic (ROC), Brier score, calibration curves, and decision curve analysis (DCA).

RESULTS: In the training cohort, the varix-specific radiomics signature developed via the least absolute shrinkage and selection operator (LASSO) demonstrated excellent discriminative power (cross-validated AUC: 0.956; 95% CI 0.872-1.000). In the temporal validation cohort, this model maintained high generalizability, yielding an AUC of 0.926 (95% CI 0.846-0.984, sensitivity: 93.1%, specificity: 71.4%) as well as a Brier score of 0.1186 and good calibration (intercept = -0.157, slope = 1.354). Surface-to-Volume Ratio (SVR) and NGTDM Coarseness are feasible radiomics.

CONCLUSION: The varix-specific radiomics model provides highly sensitive and mathematically stable non-invasive risk stratification for EV bleeding in patients with HCC.

来源:Abdom Radiol (NY),查看原文。版权归原作者所有。

引用

  1. Li, Ma, Chang, et al. Machine learning-based CT radiomics for identifying high risk esophageal varices of bleeding in hepatocellular carcinoma. Abdom Radiol (NY). 2026. PMID: 42900382. doi:10.1007/s00261-026-05808-3

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。