文献速递肿瘤 PET/CT核素与放射性配体治疗

局部晚期宫颈癌18F-FDG PET/CT与MRI放射组学模型预测腹主动脉旁淋巴结受累的多中心开发与评估

Multicentric development and evaluation of 18F-FDG PET/CT and MRI radiomics models to predict para-aortic lymph node involvement in locally advanced cervical cancer.
PubMed 文献 · Eur J Nucl Med Mol Imaging · 2023-03-09

本研究回顾性收集2个中心178例(60%训练、40%测试)及2个外部测试队列61例局部晚期宫颈癌患者,基于治疗前18F-FDG PET/CT和MRI原发肿瘤放射组学特征结合临床参数构建神经网络模型预测腹主动脉旁淋巴结(PALN)受累。临床模型训练集C-statistic为0.80(95%CI 0.71,0.87),但测试集和外部测试集仅0.57–0.67(95%CI 0.36,0.83);ComBat-放射组学模型和ComBat-联合模型在测试集C-statistic分别为0.88–0.96(95%CI 0.76,1.00)和0.85–0.92(95%CI 0.75,0.99)。作者结论认为放射组学特征优于临床参数,并应开展前瞻性验证。

要点

  • 临床模型训练集C-statistic 0.80,测试集和外部测试集仅0.57–0.67,预测能力下降。
  • ComBat-放射组学模型测试集C-statistic 0.88–0.96,ComBat-联合模型0.85–0.92。
  • 仅勾画原发肿瘤体积,放射组学特征用Radiomics toolbox®提取。

核心结论

  • 作者结论认为,从放疗前模拟或数字18F-FDG PET/CT提取的放射组学特征在决定是否行腹主动脉旁淋巴结分期或扩大野照射至PALN方面优于临床参数。
  • 作者提出现在应开展模型的前瞻性验证。

研究设计与样本

  • 回顾性收集2个中心178例局部晚期宫颈癌患者,60%用于训练、40%用于测试。
  • 另设2个外部测试队列共61例,患者来自2010年至2022年。
  • 患者均接受治疗前模拟或数字18F-FDG PET/CT、盆腔MRI及手术PALN分期。
  • 仅勾画原发肿瘤体积,放射组学特征用Radiomics toolbox®提取。
  • 采用ComBat harmonization方法减少中心间批次效应,并用神经网络方法训练临床、放射组学及联合模型。

主要发现

  • 训练集(n=102)中临床模型对PALN受累风险预测良好,C-statistic为0.80(95%CI 0.71,0.87)。
  • 临床模型在测试集(n=76)和外部测试集(n=30和n=31)的C-statistic仅为0.57至0.67(95%CI 0.36,0.83)。
  • ComBat-放射组学模型(GLDZM_HISDE_PET_FBN64和Shape_maxDiameter2D3_PET_FBW0.25)在训练集预测能力很高,测试集C-statistic为0.88至0.96(95%CI 0.76,1.00)。
  • ComBat-联合模型(FIGO 2018及相同放射组学特征)在训练集预测能力很高,测试集C-statistic为0.85至0.92(95%CI 0.75,0.99)。

关键数值与推荐

  • 临床模型训练集C-statistic 0.80(95%CI 0.71,0.87),测试集和外部测试集C-statistic 0.57–0.67(95%CI 0.36,0.83)。
  • ComBat-放射组学模型测试集C-statistic 0.88–0.96(95%CI 0.76,1.00)。
  • ComBat-联合模型测试集C-statistic 0.85–0.92(95%CI 0.75,0.99)。

临床怎么用

  • 作者结论认为放射组学特征在决定是否行腹主动脉旁淋巴结分期或扩大野照射至PALN方面优于临床参数。
  • 作者提出现在应开展模型的前瞻性验证。

局限性

  • 作者提出现在应开展模型的前瞻性验证。

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 para-aortic lymph node (PALN) involvement in patients with locally advanced cervical cancer (LACC) before chemoradiotherapy (CRT) using 18F-FDG PET/CT and MRI radiomics combined with clinical parameters. METHODS: We retrospectively collected 178 patients (60% for training and 40% for testing) in 2 centers and 61 patients corresponding to 2 further external testing cohorts with LACC between 2010 to 2022 and who had undergone pretreatment analog or digital 18F-FDG PET/CT, pelvic MRI and surgical PALN staging. Only primary tumor volumes were delineated. Radiomics features were extracted using the Radiomics toolbox®. The ComBat harmonization method was applied to reduce the batch effect between centers. Different prediction models were trained using a neural network approach with either clinical, radiomics or combined models. They were then evaluated on the testing and external validation sets and compared. RESULTS: In the training set (n = 102), the clinical model achieved a good prediction of the risk of PALN involvement with a C-statistic of 0.80 (95% CI 0.71, 0.87). However, it performed in the testing (n = 76) and external testing sets (n = 30 and n = 31) with C-statistics of only 0.57 to 0.67 (95% CI 0.36, 0.83). The ComBat-radiomic (GLDZM_HISDE_PET_FBN64 and Shape_maxDiameter2D3_PET_FBW0.25) and ComBat-combined (FIGO 2018 and same radiomics features) models achieved very high predictive ability in the training set and both models kept the same performance in the testing sets, with C-statistics from 0.88 to 0.96 (95% CI 0.76, 1.00) and 0.85 to 0.92 (95% CI 0.75, 0.99), respectively. CONCLUSIONS: Radiomic features extracted from pre-CRT analog and digital 18F-FDG PET/CT outperform clinical parameters in the decision to perform a para-aortic node staging or an extended field irradiation to PALN. 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, Bourbonne V, Pleyers C, et al. Multicentric development and evaluation of 18F-FDG PET/CT and MRI radiomics models to predict para-aortic lymph node involvement in locally advanced cervical cancer. Eur J Nucl Med Mol Imaging. 2023. PMID: 36892667. doi:10.1007/s00259-023-06180-w

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。