文献速递肿瘤 PET/CT

18F-FDG PET 强度归一化对口咽鳞状细胞癌影像组学特征及机器学习生成生物标志物的影响

Impact of 18F-FDG PET Intensity Normalization on Radiomic Features of Oropharyngeal Squamous Cell Carcinomas and Machine Learning-Generated Biomarkers.
PubMed 文献 · J Nucl Med · 2024-05-01

本研究提取430例口咽鳞状细胞癌原发肿瘤的1,037个18F-FDG PET影像组学特征,评估3种强度归一化图像与原始PET数据间特征的可重复性,并分析归一化对特征预测HPV状态效用的影响。仅34.3%特征在高可重复性水平,归一化技术选择可能影响影像组学特征对HPV的预测价值。

要点

  • 1,037个特征中仅356个(34.3%)在不同强度归一化方法间达到高可重复性(ICC≥0.90)。
  • 以豆状核归一化的特征与HPV状态关联最强,865/1,037(83.4%)特征经多重检验校正后显著。
  • 豆状核归一化XGBoost模型在训练队列交叉验证中平均AUC数值最高为0.72(SD 0.07),独立验证AUC 0.73(95%CI 0.60-0.85),外部验证AUC 0.76(95%CI 0.58-0.95)。

核心结论

  • 仅约三分之一特征在强度归一化技术间表现出高可重复性,统一归一化是实现影像组学标志物个体间可比性的前提。
  • 归一化技术的选择可能影响影像组学特征对HPV状态的预测价值。
  • 结果提示以豆状核归一化可能改善模型性能,但作者指出需更多证据才能得出确定结论。

研究设计与样本

  • 研究提取430例口咽鳞状细胞癌原发肿瘤的1,037个18F-FDG PET影像组学特征,量化形状、强度和纹理。
  • 比较3种强度归一化图像(体重SUV、以脑豆状核和小脑为参考组织的活性比值)与原始PET数据间特征的可重复性,采用组内相关系数(ICC)评估。
  • 通过单变量逻辑回归、受试者工作特征分析和极端梯度提升(XGBoost)机器学习分类器,分析强度归一化对特征预测HPV状态效用的影响。

主要发现

  • 1,037个特征中,跨归一化方法达到高(ICC≥0.90)、中(0.90>ICC≥0.75)、低(ICC<0.75)可重复性的分别有356个(34.3%)、608个(58.6%)、73个(7%)。
  • 单变量分析中,以豆状核归一化的PET特征与HPV状态关联最强,1,037个特征中865个(83.4%)经多重检验校正后显著,中位AUC为0.65(四分位距0.62-0.68)。
  • XGBoost模型中观察到相似趋势,豆状核归一化模型在训练队列交叉验证中平均AUC数值最高为0.72(SD 0.07)。
  • 该模型在验证队列中泛化良好,独立验证AUC为0.73(95%CI 0.60-0.85),外部验证AUC为0.76(95%CI 0.58-0.95)。
  • XGBoost模型间的AUC无显著差异。

关键数值与推荐

  • 可重复性分级:高ICC≥0.90,中0.90>ICC≥0.75,低ICC<0.75。
  • 单变量分析中豆状核归一化特征经多重检验校正后显著者865/1,037(83.4%),中位AUC 0.65(四分位距0.62-0.68)。
  • XGBoost豆状核归一化模型训练队列交叉验证平均AUC 0.72(SD 0.07),独立验证AUC 0.73(95%CI 0.60-0.85),外部验证AUC 0.76(95%CI 0.58-0.95)。

临床怎么用

  • 原文未据此给出临床推荐。

局限性

  • 作者指出结果仅显示趋势,需更多证据才能得出确定结论。

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

We aimed to investigate the effects of 18F-FDG PET voxel intensity normalization on radiomic features of oropharyngeal squamous cell carcinoma (OPSCC) and machine learning-generated radiomic biomarkers. Methods: We extracted 1,037 18F-FDG PET radiomic features quantifying the shape, intensity, and texture of 430 OPSCC primary tumors. The reproducibility of individual features across 3 intensity-normalized images (body-weight SUV, reference tissue activity ratio to lentiform nucleus of brain and cerebellum) and the raw PET data was assessed using an intraclass correlation coefficient (ICC). We investigated the effects of intensity normalization on the features' utility in predicting the human papillomavirus (HPV) status of OPSCCs in univariate logistic regression, receiver-operating-characteristic analysis, and extreme-gradient-boosting (XGBoost) machine-learning classifiers. Results: Of 1,037 features, a high (ICC ≥ 0.90), medium (0.90 > ICC ≥ 0.75), and low (ICC < 0.75) degree of reproducibility across normalization methods was attained in 356 (34.3%), 608 (58.6%), and 73 (7%) features, respectively. In univariate analysis, features from the PET normalized to the lentiform nucleus had the strongest association with HPV status, with 865 of 1,037 (83.4%) significant features after multiple testing corrections and a median area under the receiver-operating-characteristic curve (AUC) of 0.65 (interquartile range, 0.62-0.68). Similar tendencies were observed in XGBoost models, with the lentiform nucleus-normalized model achieving the numerically highest average AUC of 0.72 (SD, 0.07) in the cross validation within the training cohort. The model generalized well to the validation cohorts, attaining an AUC of 0.73 (95% CI, 0.60-0.85) in independent validation and 0.76 (95% CI, 0.58-0.95) in external validation. The AUCs of the XGBoost models were not significantly different. Conclusion: Only one third of the features demonstrated a high degree of reproducibility across intensity-normalization techniques, making uniform normalization a prerequisite for interindividual comparability of radiomic markers. The choice of normalization technique may affect the radiomic features' predictive value with respect to HPV. Our results show trends that normalization to the lentiform nucleus may improve model performance, although more evidence is needed to draw a firm conclusion.

来源:J Nucl Med,查看原文。版权归原作者所有。

引用

  1. Haider SP, Zeevi T, Sharaf K, et al. Impact of 18F-FDG PET Intensity Normalization on Radiomic Features of Oropharyngeal Squamous Cell Carcinomas and Machine Learning-Generated Biomarkers. J Nucl Med. 2024. PMID: 38514087. doi:10.2967/jnumed.123.266637

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。