文献速递腹部CT

CT影像组学联合临床特征预测胰腺癌同时性肝转移

Predicting Synchronous Liver Metastasis in Pancreatic Cancer Using CT Radiomics and Clinical Features: A Machine Learning Approach.
PubMed 文献 · Acad Radiol · 2026-08-25

回顾性纳入340例胰腺导管腺癌患者(190例有同时性肝转移,150例无),筛选5个影像组学特征并结合年龄、CEA、临床N分期构建26个机器学习模型。在独立验证队列(n=102)中,LDA的AUC为0.828,MLP为0.822,均显示良好校准和临床净获益。MLP在各临床亚组中表现更稳定,有助于个体化风险评估。

要点

  • 临床N分期在LDA模型中权重最高,CEA和影像组学特征在MLP模型中作用更突出
  • 淋巴结阴性亚组(AUC=0.50)和胰头肿瘤亚组(AUC=0.62)中LDA表现差,MLP更稳定
  • 低风险评分支持随访观察,高风险评分提示需活检或新辅助治疗

核心结论

  • 整合模型可实现胰腺癌同时性肝转移的术前准确预测,LDA验证队列AUC为0.828(95%CI:0.735-0.897),MLP为0.822(95%CI:0.732-0.895)。
  • 非线性MLP模型在临床亚组间稳定性优于线性LDA模型(亚组AUC为0.66-0.77)。
  • 该工具旨在辅助CT上不确定的亚厘米级肝脏病灶的临床决策,而非替代病理诊断。

研究设计与样本

  • 回顾性研究,纳入340例胰腺导管腺癌患者(190例有同时性肝转移,150例无)。
  • 采用最小冗余最大相关性和最小绝对收缩选择算子方法筛选出5个影像组学特征。
  • 基于独立临床预测因子(年龄、CEA、临床N分期)和影像组学特征构建26个机器学习模型。
  • 在独立验证队列(n=102)中,用ROC曲线、校准曲线、决策曲线分析和SHAP分析评估最优LDA和MLP模型。

关键影像表现/征象

  • SHAP分析显示临床N分期主导LDA模型,CEA和影像组学特征在MLP模型中贡献更显著。
  • Friedman的H统计量识别出5个显著的特征交互作用。

诊断标准与关键数值

  • 验证队列中LDA模型AUC为0.828(95%CI:0.735-0.897),Hosmer-Lemeshow检验P=0.551,Brier评分=0.168。
  • 验证队列中MLP模型AUC为0.822(95%CI:0.732-0.895),Hosmer-Lemeshow检验P=0.682,Brier评分=0.172。
  • 临床列线图在验证队列中AUC为0.788。
  • 亚组分析中MLP保持稳定表现(AUC为0.66-0.77),LDA在淋巴结阴性亚组AUC=0.50,胰头肿瘤亚组AUC=0.62。

临床应用与阅片要点

  • 对于CT上不确定的亚厘米级肝脏病灶,低风险评分支持随访观察,避免不必要的活检。
  • 高风险评分提示需进行确诊性活检或转向新辅助全身治疗。
  • MLP模型跨亚组稳定性更好,对淋巴结阴性及胰头肿瘤患者风险评估更可靠。
  • 该模型用于辅助临床决策,不能替代病理诊断。

局限性

  • 回顾性研究设计存在选择偏倚风险。
  • LDA模型在淋巴结阴性亚组(AUC=0.50)和胰头肿瘤亚组(AUC=0.62)表现欠佳。

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: To address the challenge of preoperative prediction of synchronous liver metastasis (LM) in pancreatic cancer (PC), we developed and validated machine learning models integrating clinical and computed tomography (CT) radiomics features, and compared the performance and interpretability of linear (linear discriminant analysis [LDA]) versus nonlinear (multilayer perceptron [MLP]) architectures.

MATERIALS AND METHODS: This retrospective study enrolled 340 patients with pancreatic ductal adenocarcinoma (190 with LM, 150 without). Five radiomics features were selected using the minimum redundancy maximum relevance and least absolute shrinkage and selection operator methods. Based on independent clinical predictors (age, carcinoembryonic antigen [CEA], and clinical N stage) and the selected radiomics features, 26 machine learning models were constructed. The optimal models (LDA and MLP) were evaluated in an independent validation cohort (n = 102) using receiver operating characteristic curves, calibration, decision curve analysis, and SHAP (SHapley Additive exPlanations) analysis.

RESULTS: In the validation cohort, LDA achieved an area under the curve (AUC) of 0.828 (95% confidence interval [CI]: 0.735-0.897), and MLP achieved 0.822 (95% CI: 0.732-0.895). Both models demonstrated good calibration, with Hosmer-Lemeshow test P values of 0.551 (Brier score = 0.168) for LDA and 0.682 (Brier score = 0.172) for MLP, alongside high net clinical benefit. SHAP analysis revealed that clinical N stage dominated the LDA model, whereas CEA and radiomics features played more prominent roles in the MLP model. Friedman's H-statistic identified five significant feature interactions. Subgroup analysis showed that MLP maintained stable performance (AUC 0.66-0.77), whereas LDA performed poorly in the lymph-node-negative (AUC = 0.50) and pancreatic head tumor (AUC = 0.62) subgroups. The clinical nomogram achieved an AUC of 0.788 in the validation cohort.

CONCLUSION: The integrated model enables accurate preoperative prediction of synchronous LM in PC. Rather than replacing pathological diagnosis, this tool is designed to assist clinical decision-making in the common dilemma of indeterminate subcentimeter liver lesions on CT: a low-risk score supports surveillance and spares unnecessary biopsy, whereas a high-risk score prompts confirmatory biopsy or a shift toward neoadjuvant systemic therapy. Both architectures exhibit robust discrimination and clinical utility; however, the nonlinear MLP model shows superior stability across clinical subgroups, offering a promising tool for individualized risk assessment and treatment planning.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Han, Xiang, Jing, et al. Predicting Synchronous Liver Metastasis in Pancreatic Cancer Using CT Radiomics and Clinical Features: A Machine Learning Approach. Acad Radiol. 2026. PMID: 42642322. doi:10.1016/j.acra.2026.08.028

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。