文献速递腹部CT

CT 栖息地分析术前预测胃癌组织学分化

Interpretable CT habitat analysis for preoperative prediction of histological differentiation in gastric cancer.
PubMed 文献 · Eur J Radiol · 2026-09-09

本研究回顾性纳入两家中心 978 例病理确诊胃癌患者,基于术前静脉期 CT 行 K-means 栖息地分析并联合临床特征建立列线图。结果显示栖息地模型及联合模型在训练、测试与外部验证队列中均有较好预测效能,栖息地特征对预测贡献最大。

要点

  • 静脉期 CT 栖息地特征可术前预测胃癌组织学分化。
  • 联合年龄、性别、部位、CT 分期、CA19-9 的列线图预测效能优于单用栖息地或临床模型。
  • 栖息地聚类 k=2 为最佳划分。

核心结论

  • CT 栖息地分析可术前较准确预测胃癌组织学分化,联合临床变量可进一步提高预测效能。

研究设计与样本

  • 回顾性研究,共纳入 978 例病理确诊胃癌患者,来自两家中心。
  • 中心 1 患者 678 例随机分为训练队列 406 例与测试队列 272 例,中心 2 患者 300 例作为外部验证队列。
  • 临床模型采用多因素 logistic 回归筛选独立预测因子,栖息地特征提取自术前静脉期 CT K-means 聚类。

关键影像表现/征象

  • 肿瘤栖息地由术前静脉期 CT 通过 K-means 聚类生成,最佳聚类数为 k=2。
  • SHAP 分析显示栖息地衍生特征是模型预测的最强贡献因素。

诊断标准与关键数值

  • 组织学分化的独立预测因子为年龄、性别、肿瘤位置、CT 所见 T 分期、CT 所见 N 分期及 CA19-9 水平。
  • 训练队列:临床模型 AUC 0.747(95% CI: 0.700-0.794),栖息地模型 AUC 0.835(0.794-0.874),列线图模型 AUC 0.872(0.836-0.904)。
  • 测试队列:临床模型 AUC 0.652(0.585-0.716),栖息地模型 AUC 0.778(0.723-0.831),列线图模型 AUC 0.803(0.745-0.855)。
  • 外部验证队列:临床模型 AUC 0.682(0.620-0.738),栖息地模型 AUC 0.831(0.780-0.881),列线图模型 AUC 0.839(0.791-0.887)。

临床应用与阅片要点

  • 日常阅片时可关注静脉期 CT 肿瘤内部异质性,栖息地分析提示不同亚区域对分化预测有差异。
  • 报告胃癌 CT 分期时应同时记录肿瘤位置,因其是组织学分化的独立预测因子。
  • 联合临床与影像栖息地特征的列线图可用于术前风险评估,辅助治疗决策。

局限性

  • 本研究为回顾性设计,可能存在选择偏倚。

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 an interpretable preoperative model for predicting histological differentiation in gastric cancer using CT habitat analysis combined with clinical features.

METHODS: This retrospective study included 978 patients with pathologically confirmed gastric cancer from two institutions. Patients from Center 1 (n = 678) were randomly divided into a training cohort (n = 406) and a testing cohort (n = 272), while patients from Center 2 (n = 300) served as an external validation cohort. Independent clinical predictors of histological differentiation were identified using multivariable logistic regression to construct a clinical model. Tumor habitats were generated from preoperative venous-phase CT using K-means clustering, and habitat scores, subregional volumes, and volume fractions were extracted to develop a Habitat model. Clinical and habitat features were then integrated into a nomogram.

RESULTS: Age, sex, tumor location, CT-detected T stage, CT-detected N stage, and CA19-9 level were independent predictors of histological differentiation. The optimal habitat partition was achieved with two clusters (k = 2) according to the Calinski-Harabasz index. In the training cohort, area under the receiver operating characteristic curve (AUC) were 0.747 (95% CI: 0.700-0.794) for the Clinical model, 0.835 (0.794-0.874) for the Habitat model, and 0.872 (0.836-0.904) for the Nomogram model. In the testing cohort, corresponding AUCs were 0.652 (0.585-0.716), 0.778 (0.723-0.831), and 0.803 (0.745-0.855). In the external validation cohort, AUCs were 0.682 (0.620-0.738), 0.831 (0.780-0.881), and 0.839 (0.791-0.887), respectively. SHapley Additive exPlanations (SHAP) analysis identified habitat-derived features as the strongest contributors to model predictions.

CONCLUSION: CT habitat analysis enables accurate preoperative prediction of histological differentiation in gastric cancer. Incorporating clinical variables further improves performance.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Yao, Zheng, Xu, et al. Interpretable CT habitat analysis for preoperative prediction of histological differentiation in gastric cancer. Eur J Radiol. 2026. PMID: 42731502. doi:10.1016/j.ejrad.2026.113231

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。