文献速递腹部泌尿生殖MR

基于DKI的临床-影像组学模型术前预测结直肠癌淋巴结转移

Diffusion Kurtosis Imaging-Based Radiomics for Preoperative Prediction of Lymph Node Metastasis in Colon and Rectal Cancer.
PubMed 文献 · Acad Radiol · 2026-07-17

本研究纳入204例未经治疗的结直肠癌患者(结肠癌108例,直肠癌96例),从原发肿瘤的ADC、DKI_D和DKI_K图中提取影像组学特征。采用套索回归筛选特征并构建多个模型,联合DKI影像组学评分与区域淋巴结最大短径的Combined模型区分度最佳。该模型在训练集和测试集AUC分别为0.939和0.957,可为结直肠癌淋巴结转移提供无创预测。

要点

  • 联合DKI影像组学评分与区域淋巴结最大短径的模型预测效能最高,测试集AUC达0.957。
  • DKI参数图(ADC、DKI_D、DKI_K)提取的影像组学特征对淋巴结转移有增量预测价值。
  • 模型在结肠癌(AUC 0.980)和直肠癌(AUC 0.932)亚组中均表现良好。

核心结论

  • 联合DKI影像组学评分与区域淋巴结最大短径的Combined模型对结直肠癌淋巴结转移具有较高的术前预测效能。
  • Combined模型在训练集AUC为0.939(95% CI: 0.906-0.968),在测试集AUC为0.957(95% CI: 0.906-0.996),优于单参数模型。

研究设计与样本

  • 本研究为204例未经治疗的结直肠癌患者(结肠癌108例,直肠癌96例)的回顾性研究。
  • 从原发肿瘤的ADC、DKI_D和DKI_K参数图中提取影像组学特征,采用最小绝对收缩和选择算子回归进行特征选择。
  • 分别采用逻辑回归、径向基函数支持向量机和朴素贝叶斯构建ADC、DKI_D、DKI_K及DKI模型,采用逻辑回归构建临床模型和Combined模型。
  • 模型性能通过ROC分析、校准曲线和决策曲线分析评估,模型可解释性通过SHAP分析评估。

关键影像表现/征象

  • 影像组学特征提取自原发肿瘤的ADC、DKI_D(平均扩散率)和DKI_K(平均峰度)参数图。
  • 临床特征纳入区域淋巴结最大短径。

诊断标准与关键数值

  • Combined模型在训练集AUC为0.939(95% CI: 0.906-0.968),测试集AUC为0.957(95% CI: 0.906-0.996)。
  • Combined模型优于单参数模型(p < 0.05)。
  • 结肠癌亚组AUC为0.980,直肠癌亚组AUC为0.932。

临床应用与阅片要点

  • DKI参数图影像组学联合区域淋巴结短径可为结直肠癌术前淋巴结分期提供辅助信息。
  • SHAP分析显示DKI特征对模型预测有增量价值,提示弥散峰度成像参数应被纳入影像组学分析。
  • 模型有助于个体化风险分层和治疗方案制定。

局限性

  • 原文未报告该研究的具体局限性。

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 develop a diffusion kurtosis imaging (DKI)-based clinical-radiomics model for the preoperative prediction of lymph node metastasis (LNM) in colon and rectal cancer.

MATERIALS AND METHODS: 204 treatment-naive colorectal cancer (CRC) patients (108 colon, 96 rectal) were included. Radiomic features were extracted from apparent diffusion coefficient (ADC), mean diffusivity (DKI_D), and mean kurtosis (DKI_K) maps of primary tumors. Least absolute shrinkage and selection operator regression was used for feature selection. Logistic regression (LR), radial basis function support vector machine, and Naive Bayes were used to construct the ADC, DKI_D, DKI_K, and DKI models. LR was performed to construct the clinical and Combined models. The model performance was evaluated using receiver operating characteristic (ROC) analysis, calibration, and decision curve analysis. The model interpretability was assessed using Shapley additive explanations (SHAP).

RESULTS: The Combined model, integrating the DKI-derived radiomics score with maximum short-axis diameter of regional lymph nodes, achieved the highest discrimination, with area under the ROC curve (AUC) of 0.939 (95% CI: 0.906-0.968) in training and 0.957 (95% CI: 0.906-0.996) in testing, outperforming single-parameter models (p < 0.05). Subgroup analyses showed high performance in colon (AUC 0.980) and rectal (AUC 0.932) cancer. SHAP analysis confirmed the added value of DKI features.

CONCLUSION: The Combined model provides promising noninvasive prediction of LNM in colon and rectal cancer, aiding individualized risk stratification and treatment planning.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Liu, Zhuang, Gong, et al. Diffusion Kurtosis Imaging-Based Radiomics for Preoperative Prediction of Lymph Node Metastasis in Colon and Rectal Cancer. Acad Radiol. 2026. PMID: 42469043. doi:10.1016/j.acra.2026.06.032

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。