文献速递肿瘤 PET/CT

比较病灶与特征选择方法用FDG PET/CT影像组学特征预测新诊断DLBCL患者进展

Comparing lesion and feature selections to predict progression in newly diagnosed DLBCL patients with FDG PET/CT radiomics features.
PubMed 文献 · Eur J Nucl Med Mol Imaging · 2022-08-04

本研究纳入296例新诊断DLBCL患者,从基线[18F]-FDG PET/CT提取485个影像组学特征及18个播散特征,比较不同病灶选择与特征降维方法对2年后进展的预测价值,采用五折交叉验证50次重复计算平均CV-AUC。结果显示常规PET与播散特征模型预测价值最高(CV-AUC 0.72-0.75),播散特征相对重要性最高,无病灶选择方法显著优于既往模型,过采样联合递归特征消除获得最高CV-AUC。

要点

  • 常规PET与播散特征模型预测价值最高,CV-AUC为0.72-0.75
  • 播散特征在这些模型中具有最高相对重要性
  • 无病灶选择方法显著优于既往模型,过采样联合RFE获得最高CV-AUC

核心结论

  • 无论采用何种病灶选择、特征选择或特征降维方法,患者水平常规PET特征与播散特征均具有最高预测价值。

研究设计与样本

  • 研究纳入296例新诊断DLBCL患者,从基线[18F]-FDG PET/CT提取485个影像组学特征(5个常规PET、22个形态学、50个强度、408个纹理)及18个患者水平播散特征。
  • 测试多种病灶选择方法(最大或最热病灶、患者水平[含或不含播散特征]、所有病灶的最大值或中位数),并与既往发表模型的预测价值比较。
  • 应用主成分分析、递归特征消除(RFE)、因子分析和单变量选择等数据降维方法,采用五折交叉验证50次重复(含或不含过采样)计算平均交叉验证AUC(CV-AUC)。

主要发现

  • 常规PET与播散特征模型的预测价值最高,CV-AUC为0.72-0.75。
  • 播散特征在这些模型中具有最高相对重要性。
  • 与既往模型相比,没有任何病灶选择方法显示出显著更高的预测价值。
  • 过采样联合RFE获得最高的CV-AUC。

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)。

原文

PURPOSE: Biomarkers that can accurately predict outcome in DLBCL patients are urgently needed. Radiomics features extracted from baseline [18F]-FDG PET/CT scans have shown promising results. This study aims to investigate which lesion- and feature-selection approaches/methods resulted in the best prediction of progression after 2 years. METHODS: A total of 296 patients were included. 485 radiomics features (n = 5 conventional PET, n = 22 morphology, n = 50 intensity, n = 408 texture) were extracted for all individual lesions and at patient level, where all lesions were aggregated into one VOI. 18 features quantifying dissemination were extracted at patient level. Several lesion selection approaches were tested (largest or hottest lesion, patient level [all with/without dissemination], maximum or median of all lesions) and compared to the predictive value of our previously published model. Several data reduction methods were applied (principal component analysis, recursive feature elimination (RFE), factor analysis, and univariate selection). The predictive value of all models was tested using a fivefold cross-validation approach with 50 repeats with and without oversampling, yielding the mean cross-validated AUC (CV-AUC). Additionally, the relative importance of individual radiomics features was determined. RESULTS: Models with conventional PET and dissemination features showed the highest predictive value (CV-AUC: 0.72-0.75). Dissemination features had the highest relative importance in these models. No lesion selection approach showed significantly higher predictive value compared to our previous model. Oversampling combined with RFE resulted in highest CV-AUCs. CONCLUSION: Regardless of the applied lesion selection or feature selection approach and feature reduction methods, patient level conventional PET features and dissemination features have the highest predictive value. Trial registration number and date: EudraCT: 2006-005174-42, 01-08-2008.

来源:Eur J Nucl Med Mol Imaging,查看原文。版权归原作者所有。

引用

  1. Eertink JJ, Zwezerijnen GJC, Cysouw MCF, et al. Comparing lesion and feature selections to predict progression in newly diagnosed DLBCL patients with FDG PET/CT radiomics features. Eur J Nucl Med Mol Imaging. 2022. PMID: 35925442. doi:10.1007/s00259-022-05916-4

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。