文献速递腹部MR

基于MRI的影像组学标签:预测混合型肝细胞-胆管细胞癌微血管侵犯的潜在影像生物标志物

MRI-based radiomics signature: a potential imaging biomarker for prediction of microvascular invasion in combined hepatocellular-cholangiocarcinoma.
PubMed 文献 · Abdom Radiol (NY) · 2023-10-13

本研究纳入91例经组织学确诊的混合型肝细胞-胆管细胞癌患者,术前行动态对比增强MRI,分为训练队列(MVI阳性27例、阴性37例)和验证队列(MVI阳性11例、阴性16例)。采用LASSO算法构建由4个稳定影像组学特征组成的标签,训练队列AUC为0.866(95%CI 0.757-0.938),验证队列AUC为0.841(95%CI 0.650-0.952)。结论认为该影像组学标签可作为术前预测MVI的可靠影像生物标志物。

要点

  • 训练队列中肿瘤较大和Radscore较高与MVI存在相关(p=0.026和<0.001),验证队列亦证实(p=0.040和0.001)。
  • 基于DCE-MRI的4个稳定影像组学特征构建的标签,训练队列AUC为0.866(95%CI 0.757-0.938)。
  • 验证队列AUC为0.841(95%CI 0.650-0.952),原文结论认为该标签可作为术前预测MVI的可靠影像生物标志物。

核心结论

  • 基于DCE-MRI构建的影像组学标签可作为术前预测混合型肝细胞-胆管细胞癌微血管侵犯的可靠影像生物标志物。

研究设计与样本

  • 研究纳入91例经组织学确诊的混合型肝细胞-胆管细胞癌患者,术前均行肝脏DCE-MRI,分为训练队列(MVI阳性27例、阴性37例)和验证队列(MVI阳性11例、阴性16例)。

关键影像表现/征象

  • 训练队列中肿瘤较大与MVI存在相关(p=0.026),验证队列亦证实(p=0.040)。
  • 训练队列中Radscore较高与MVI存在相关(p<0.001),验证队列亦证实(p=0.001)。

诊断标准与关键数值

  • 影像组学标签由4个稳定影像组学特征组成,训练队列AUC=0.866(95%CI 0.757-0.938,p<0.001)。
  • 验证队列AUC=0.841(95%CI 0.650-0.952,p<0.001)。

临床应用与阅片要点

  • 原文结论认为,基于DCE-MRI的影像组学标签可作为术前预测混合型肝细胞-胆管细胞癌MVI的可靠影像生物标志物。

局限性

  • 原文未报告局限性。

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

PURPOSE: To investigate the potential of radiomics analysis of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) in preoperatively predicting microvascular invasion (MVI) in patients with combined hepatocellular-cholangiocarcinoma (cHCC-CC) before surgery.

METHODS: A cohort of 91 patients with histologically confirmed cHCC-CC who underwent preoperative liver DCE-MRI were enrolled and divided into a training cohort (27 MVI-positive and 37 MVI-negative) and a validation cohort (11 MVI-positive and 16 MVI-negative). Clinical characteristics and MR features of the patients were evaluated. Radiomics features were extracted from DCE-MRI, and a radiomics signature was built using the least absolute shrinkage and selection operator (LASSO) algorithm in the training cohort. Prediction performance of the developed radiomics signature was evaluated by utilizing the receiver operating characteristic (ROC) analysis.

RESULTS: Larger tumor size and higher Radscore were associated with the presence of MVI in the training cohort (p = 0.026 and < 0.001, respectively), and theses findings were also confirmed in the validation cohort (p = 0.040 and 0.001, respectively). The developed radiomics signature, composed of 4 stable radiomics features, showed high prediction performance in both the training cohort (AUC = 0.866, 95% CI 0.757-0.938, p < 0.001) and validation cohort (AUC = 0.841, 95% CI 0.650-0.952, p < 0.001).

CONCLUSIONS: The radiomics signature developed from DCE-MRI can be a reliable imaging biomarker to preoperatively predict MVI in cHCC-CC.

来源:Abdom Radiol (NY),查看原文。版权归原作者所有。

引用

  1. Zhou G, Zhou Y, Xu X, et al. MRI-based radiomics signature: a potential imaging biomarker for prediction of microvascular invasion in combined hepatocellular-cholangiocarcinoma. Abdom Radiol (NY). 2023. PMID: 37831165. doi:10.1007/s00261-023-04049-y

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。