文献速递腹部技术与安全CT

2.5D双期CT联合血清甘油三酯早期预测高甘油三酯性急性胰腺炎重症风险

Integrating 2.5D multi-modal CT imaging with serum triglycerides for early risk stratification in hypertriglyceridemia-induced acute pancreatitis: A multicenter study.
PubMed 文献 · Eur J Radiol · 2026-06-19

多中心回顾性研究纳入1518例高甘油三酯血症性急性胰腺炎患者,入院24小时内行CT平扫及增强,提取2.5D深度学习特征并与甘油三酯等指标联合建模。融合影像模型外部验证AUC为0.923和0.890,Fusion-TG模型在外部队列将重症敏感度从60.6%提升至94.4%且保持高特异度。

要点

  • 双期CT特征联合甘油三酯可明显提高重症急性胰腺炎早期敏感度
  • 增强CT特征与甘油三酯在模型中贡献最大,阅片时应重点关注
  • Fusion-TG仅需平扫、增强CT及甘油三酯,适合急诊快速分层

核心结论

  • 融合影像模型在训练队列AUC为0.966,外部验证队列AUC分别为0.923和0.890
  • Fusion-TG与Fusion-Multivar的AUC相近,均达到0.970-0.971
  • 纳入甘油三酯后外部队列重症敏感度由60.6%提高至94.4%,同时保持高特异度
  • SHAP分析显示增强CT来源特征与甘油三酯为主要预测贡献因素

研究设计与样本

  • 多中心回顾性研究,纳入1518例连续高甘油三酯血症性急性胰腺炎患者
  • 患者来自三家医院,分为训练队列990例及两个外部验证队列340例和188例
  • 入院24小时内完成CT平扫和增强CT检查
  • 采用2.5D SE-ResNet-50网络提取特征,经自监督学习预训练
  • 特征经主成分分析降维后输入支持向量机分类器,平扫与增强概率加权融合

关键影像表现/征象

  • 模型预测依据为CT平扫及增强图像中提取的深度特征,无传统影像征象报告
  • SHAP分析提示增强CT来源特征对预测重症贡献更大
  • CT严重指数作为联合模型输入变量之一参与预测

诊断标准与关键数值

  • 外部验证队列I融合影像模型AUC为0.923,队列II为0.890
  • Fusion-TG模型AUC为0.970-0.971
  • 纳入甘油三酯后外部队列敏感度为94.4%,未纳入时为60.6%
  • Fusion-Multivar联合甘油三酯、总胆固醇、合并症及CT严重指数

临床应用与阅片要点

  • 急诊高甘油三酯性急性胰腺炎患者可用平扫加增强CT及甘油三酯值快速分层重症风险
  • 增强CT信息在模型中权重更高,阅片时不应忽略增强序列
  • 单一甘油三酯与影像概率结合即可接近多变量模型性能

局限性

  • 为多中心回顾性研究,存在回顾性设计固有偏倚风险

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

OBJECTIVES: To develop and externally validate a clinical-radiological framework that fuses 2.5D deep learning features from dual-phase computed tomography (CT) with serum triglyceride (TG) levels for early prediction of severe acute pancreatitis (SAP) in patients with hypertriglyceridemia-induced acute pancreatitis (HTGP).

METHODS: In this multicenter retrospective study, 1,518 consecutive HTGP patients from three hospitals were divided into a training cohort (n = 990) and two external validation cohorts (n = 340, n = 188). Patients underwent non-enhanced CT (NECT) and enhanced CT (ECT) within 24 h of admission. A 2.5D SE-ResNet-50 network, pre-trained with self-supervised learning, extracted deep features from NECT and ECT. Features were reduced by principal component analysis and entered into support vector machine classifiers; NECT and ECT probabilities were fused by weighted averaging. Clinical-radiological models further combined imaging probability with TG alone (Fusion-TG) or with TG, total cholesterol, comorbidities, and CT severity index.

RESULTS: The fusion imaging model yielded area under the receiver operating characteristic curves (AUCs) of 0.966 in the training cohort and 0.923 and 0.890 externally. Fusion-TG and Fusion-Multivar achieved similar AUCs (0.970-0.971). Incorporating TG increased sensitivity for SAP (e.g., 60.6 % to 94.4 % in external cohort I) while preserving high specificity, and SHapley Additive exPlanations (SHAP) analysis highlighted ECT-derived features and TG as dominant contributors.

CONCLUSIONS: The parsimonious Fusion-TG model enables robust, interpretable early SAP risk stratification in HTGP using only dual-phase CT and a single biochemical marker, supporting rapid decision-making in emergency care.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Guo, Chen, Qin, et al. Integrating 2.5D multi-modal CT imaging with serum triglycerides for early risk stratification in hypertriglyceridemia-induced acute pancreatitis: A multicenter study. Eur J Radiol. 2026. PMID: 42322722. doi:10.1016/j.ejrad.2026.113028

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。