文献速递肿瘤 PET/CT

多中心开发与评估[18F]FDG PET/CT和CT影像组学模型预测接受立体定向体部放疗的早期非小细胞肺癌区域和/或远处复发

Multicentric development and evaluation of [18F]FDG PET/CT and CT radiomic models to predict regional and/or distant recurrence in early-stage non-small cell lung cancer treated by stereotactic body radiation therapy.
PubMed 文献 · Eur J Nucl Med Mol Imaging · 2023-11-21

本研究回顾性收集464例(训练60%、测试40%)来自列日大学医院及63例来自布雷斯特大学医院(外部测试集)的早期非小细胞肺癌患者,均接受立体定向体部放疗并有治疗前[18F]FDG PET/CT和计划CT。采用PyRadiomics提取影像组学特征并经ComBat协调,用神经网络构建临床、影像组学和联合模型预测区域和/或远处复发。影像组学模型在训练集和测试集C-statistic为0.70至0.78(95%CI 0.63, 0.88),优于临床模型(0.53至0.59,95%CI 0.41, 0.67),联合模型为0.50至0.62(95%CI 0.37, 0.69)。

要点

  • 治疗前[18F]FDG PET/CT和CT提取的影像组学特征预测区域和/或远处复发优于临床参数。
  • 影像组学模型在训练集和测试集C-statistic为0.70至0.78(95%CI 0.63, 0.88)。
  • 临床模型C-statistic为0.53至0.59(95%CI 0.41, 0.67),联合模型为0.50至0.62(95%CI 0.37, 0.69)。

核心结论

  • 从放疗前模拟和数字[18F]FDG PET/CT提取的影像组学特征在预测区域和/或远处复发及讨论早期非小细胞肺癌辅助全身治疗方面优于临床参数。
  • 作者认为现在应进行模型的前瞻性验证。

研究设计与样本

  • 回顾性收集列日大学医院464例患者(60%训练、40%测试)和布雷斯特大学医院63例患者(外部测试集),均为2010至2020年间接受立体定向体部放疗且有治疗前[18F]FDG PET/CT和计划CT的早期非小细胞肺癌患者。
  • 使用PyRadiomics工具箱提取影像组学特征,并应用ComBat协调方法减少中心间批次效应。
  • 采用神经网络方法训练和测试临床、影像组学和联合模型以预测区域和/或远处复发。

主要发现

  • 训练集(n=273)、测试集(n=191和n=63)中,临床模型预测区域和/或远处复发的C-statistic为0.53至0.59(95%CI 0.41, 0.67)。
  • 影像组学模型(original_firstorder_Entropy、original_gldm_LowGrayLevelEmphasis和original_glcm_DifferenceAverage)在训练集预测能力较高,在测试集保持相同性能,C-statistic为0.70至0.78(95%CI 0.63, 0.88)。
  • 联合模型表现中等,C-statistic为0.50至0.62(95%CI 0.37, 0.69)。

关键数值与推荐

  • 影像组学模型C-statistic为0.70至0.78(95%CI 0.63, 0.88),高于临床模型(0.53至0.59,95%CI 0.41, 0.67)和联合模型(0.50至0.62,95%CI 0.37, 0.69)。

临床怎么用

  • 作者认为从放疗前模拟和数字[18F]FDG PET/CT提取的影像组学特征在预测区域和/或远处复发及讨论早期非小细胞肺癌辅助全身治疗方面优于临床参数。
  • 作者认为现在应进行模型的前瞻性验证。

局限性

  • 作者在结论中提出模型需进行前瞻性验证。

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: To develop machine learning models to predict regional and/or distant recurrence in patients with early-stage non-small cell lung cancer (ES-NSCLC) after stereotactic body radiation therapy (SBRT) using [18F]FDG PET/CT and CT radiomics combined with clinical and dosimetric parameters. METHODS: We retrospectively collected 464 patients (60% for training and 40% for testing) from University Hospital of Liège and 63 patients from University Hospital of Brest (external testing set) with ES-NSCLC treated with SBRT between 2010 and 2020 and who had undergone pretreatment [18F]FDG PET/CT and planning CT. Radiomic features were extracted using the PyRadiomics toolbox®. The ComBat harmonization method was applied to reduce the batch effect between centers. Clinical, radiomic, and combined models were trained and tested using a neural network approach to predict regional and/or distant recurrence. RESULTS: In the training (n = 273) and testing sets (n = 191 and n = 63), the clinical model achieved moderate performances to predict regional and/or distant recurrence with C-statistics from 0.53 to 0.59 (95% CI, 0.41, 0.67). The radiomic (original_firstorder_Entropy, original_gldm_LowGrayLevelEmphasis and original_glcm_DifferenceAverage) model achieved higher predictive ability in the training set and kept the same performance in the testing sets, with C-statistics from 0.70 to 0.78 (95% CI, 0.63, 0.88) while the combined model performs moderately well with C-statistics from 0.50 to 0.62 (95% CI, 0.37, 0.69). CONCLUSION: Radiomic features extracted from pre-SBRT analog and digital [18F]FDG PET/CT outperform clinical parameters in the prediction of regional and/or distant recurrence and to discuss an adjuvant systemic treatment in ES-NSCLC. Prospective validation of our models should now be carried out.

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

引用

  1. Lucia F, Louis T, Cousin F, et al. Multicentric development and evaluation of [18F]FDG PET/CT and CT radiomic models to predict regional and/or distant recurrence in early-stage non-small cell lung cancer treated by stereotactic body radiation therapy. Eur J Nucl Med Mol Imaging. 2023. PMID: 37987783. doi:10.1007/s00259-023-06510-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。