文献速递腹部CT

CT栖息地分析与深度学习预测局部进展期胃癌LVI/PNI

Preoperative prediction of lymphovascular and perineural invasion in locally advanced gastric cancer via CT habitat analysis and deep learning: A dual-center study.
PubMed 文献 · Eur J Radiol · 2026-06-24

这项双中心回顾性研究纳入611例局部进展期胃癌患者,从静脉期CT全瘤图像提取影像组学与深度学习特征,并通过K-means划分肿瘤栖息地亚区。整合深度学习签名、全瘤栖息地签名、cT分期与组织学分级的联合模型在训练、内部验证和外部验证队列的AUC分别为0.891、0.866和0.815。决策曲线分析显示该模型具有净临床获益。

要点

  • 联合模型整合CT栖息地特征与深度学习特征,用于术前预测LAGC的LVI/PNI状态
  • 静脉期CT全瘤分析即可提取有效预测特征,无需额外检查序列
  • 模型输出的列线图可辅助个体化治疗决策与术前风险评估

核心结论

  • 整合深度学习签名、全瘤栖息地签名、cT分期与组织学分级的联合模型对局部进展期胃癌LVI/PNI具有良好术前预测效能
  • 该联合模型在训练、内部验证及外部验证队列中均有较好的区分能力,AUC分别为0.891、0.866和0.815

研究设计与样本

  • 双中心回顾性研究,共纳入611例局部进展期胃癌患者
  • 患者分为训练队列374例、内部验证队列161例和外部验证队列76例
  • 从静脉期CT全瘤图像提取影像组学和深度学习特征,经多元逻辑回归构建联合模型并以列线图展示
  • 采用曲线下面积(AUC)和决策曲线分析(DCA)评估模型性能

关键影像表现/征象

  • 静脉期CT全瘤图像中深度学习签名与全瘤栖息地签名表现出较好的区分能力
  • 通过K-means聚类将肿瘤划分为不同栖息地亚区,并从中提取深度学习特征
  • 联合模型整合了全瘤深度学习签名、全瘤栖息地签名、cT分期与组织学分级

诊断标准与关键数值

  • 训练队列AUC为0.891
  • 内部验证队列AUC为0.866
  • 外部验证队列AUC为0.815
  • 纳入联合模型的临床因素为cT分期和组织学分级

临床应用与阅片要点

  • 该模型可以术前无创评估局部进展期胃癌的LVI/PNI风险,辅助制定个体化治疗策略
  • 静脉期CT图像即可完成分析,与常规胃癌术前CT检查流程兼容
  • 列线图形式便于在临床工作中量化个体患者的LVI/PNI风险

局限性

  • 研究为回顾性设计,可能存在选择偏倚
  • 外部验证队列样本量较小,仅76例

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: To develop and validate a combined model integrating CT-based habitat analysis and deep learning (DL) features for the preoperative prediction of lymphovascular and perineural invasion (LVI/PNI) in locally advanced gastric cancer (LAGC).

METHODS: This dual-center, retrospective study included 611 LAGC patients divided into training (n = 374), internal validation (n = 161), and external validation (n = 76) cohorts. Radiomics and DL features were extracted from venous-phase CT images of the whole tumor to identify the optimal intratumoral signature. Additionally, K-means clustering was utilized to partition the tumors into distinct habitat subregions, from which DL features were extracted to select the optimal habitat signature. A combined model integrating the best intratumoral and habitat signatures with significant clinical factors was constructed via multivariate logistic regression and visualized as a nomogram. Performance was assessed using the area under the curve (AUC) and decision curve analysis (DCA).

RESULTS: The DL signature and the whole tumor (WT) habitat signature demonstrated superior discriminatory ability. Consequently, the combined model-integrating the DL signature, habitat WT signature, cT stage, and histological grade-achieved favorable predictive efficacy, yielding numerical improvements in AUC performance across all cohorts. AUC values were 0.891, 0.866, and 0.815 for the training, internal validation, and external validation cohorts, respectively. DCA confirmed that the model provided substantial net clinical benefit.

CONCLUSION: The proposed combined model provides a promising and clinically relevant tool for preoperative LVI/PNI risk assessment in LAGC, facilitating individualized treatment strategies.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Bai, Bai, Guo, et al. Preoperative prediction of lymphovascular and perineural invasion in locally advanced gastric cancer via CT habitat analysis and deep learning: A dual-center study. Eur J Radiol. 2026. PMID: 42372557. doi:10.1016/j.ejrad.2026.113041

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。