文献速递神经MR

基于DCE-MRI和DWI的影像组学模型可能改善胶质瘤IDH1突变和血管生成的预测

A radiomics model based on DCE-MRI and DWI may improve the prediction of estimating IDH1 mutation and angiogenesis in gliomas.
PubMed 文献 · Eur J Radiol · 2022-01-01

本研究纳入100例胶质瘤患者,按7:3分为训练组和验证组,基于DCE-MRI和DWI提取影像组学特征,构建SVM模型、常规模型及联合模型(影像组学特征+年龄+强化程度),评估IDH1突变和VEGF表达。联合模型预测IDH1突变AUC最高(训练组0.967,验证组0.909);SVM模型评估VEGF表达验证组AUC为0.919。

要点

  • 联合模型(影像组学+年龄+强化程度)预测IDH1突变AUC训练组0.967、验证组0.909。
  • SVM影像组学模型评估VEGF表达验证组AUC为0.919。
  • 基于DCE-MRI和DWI的影像组学模型对评估胶质瘤IDH1突变和血管生成有相当作用。

核心结论

  • 基于DCE-MRI和DWI的影像组学模型对评估胶质瘤IDH1突变和血管生成有相当作用。

研究设计与样本

  • 纳入100例胶质瘤患者(训练组与验证组按7:3比例),采用DCE-MRI和DWI,以免疫组化为参考标准评估IDH1基因型和VEGF表达,使用3DSlicer提取影像组学特征并经Lasso降维,构建SVM模型、常规模型及联合模型。

诊断标准与关键数值

  • 联合模型预测IDH1突变AUC训练组0.967、验证组0.909;SVM模型训练组0.939、验证组0.880;常规模型训练组0.906、验证组0.842。
  • SVM模型评估胶质瘤VEGF表达验证组AUC为0.919。

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 value of a radiomics model based on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) and diffusion weighted imaging (DWI) in estimating isocitrate dehydrogenase 1 (IDH1) mutation and angiogenesis in gliomas.

METHOD: One hundred glioma patients with DCE-MRI and DWI were enrolled in this study (training and validation groups with a ratio of 7:3). The IDH1 genotypes and expression of vascular endothelial growth factor (VEGF) in gliomas were assessed by immunohistochemistry. Radiomics features were extracted by an open source software (3DSlicer) and reduced using Least absolute shrinkage and selection operator (Lasso). The support vector machine (SVM) model was developed based on the most useful predictive radiomics features. The conventional model was built by the selected clinical and morphological features. Finally, a combined model including radiomics signature, age and enhancement degree was established. Receiver operator characteristic (ROC) curve was implemented to assess the diagnostic performance of the three models.

RESULTS: For IDH1 mutation, the combined model achieved the highest area under curve (AUC) in comparison with the SVM and conventional models (training group, AUC = 0.967, 0.939 and 0.906; validation group, AUC = 0.909, 0.880 and 0.842). Furthermore, the SVM model showed good diagnostic performance in estimating gliomas VEGF expression (validation group, AUC = 0.919).

CONCLUSIONS: The radiomics model based on DCE-MRI and DWI can have a considerable effect on the evaluation of IDH1 mutation and angiogenesis in gliomas.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Wang, Hu, Zhou, et al. A radiomics model based on DCE-MRI and DWI may improve the prediction of estimating IDH1 mutation and angiogenesis in gliomas. Eur J Radiol. 2022. PMID: 34995947. doi:10.1016/j.ejrad.2021.110141

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。