文献速递肿瘤 PET/CT核素与放射性配体治疗

PET与MRI影像组学联合模型预测宫颈癌放化疗后复发的外部验证

External validation of a combined PET and MRI radiomics model for prediction of recurrence in cervical cancer patients treated with chemoradiotherapy.
PubMed 文献 · Eur J Nucl Med Mol Imaging · 2018-12-07

本研究在法国和加拿大三个中心验证了基于18F-FDG PET和MRI两个影像组学特征的模型,用于预测局部晚期宫颈癌放化疗后的无病生存(DFS)和局部区域控制(LRC)。模型在一个法国队列(n=112)中调优,并在另一个法国队列(n=50)和加拿大队列(n=28)中外部验证。DFS模型在两个验证队列中准确率达90%(95%CI [79-98%]),LRC模型在法国队列准确率98%(95%CI [90-99%]),加拿大队列96%(95%CI [80-99%])。

要点

  • 基于ADC MRI和PET两个影像组学特征的模型在外部验证中显示高准确率。
  • ComBat harmonization可显著提高模型预测准确性。
  • 标准临床变量预测准确率仅56-60%,远低于影像组学模型。

核心结论

  • 先前开发的PET/MRI影像组学预测模型在两个独立外部队列中成功验证。

研究设计与样本

  • 多中心外部验证研究,纳入接受放化疗的局部晚期宫颈癌患者,来自两个法国中心和一个加拿大中心。
  • 使用一个法国队列(n=112)调优模型,在另一个法国队列(n=50)和加拿大队列(n=28)中外部验证。
  • 采用ComBat方法对两个影像组学特征进行多中心 harmonization。

主要发现

  • DFS模型在法国和加拿大验证队列中准确率均为90%(95%CI [79-98%]),敏感度92-93%,特异度87-89%。
  • LRC模型在法国队列准确率98%(95%CI [90-99%]),敏感度86%,特异度100%;在加拿大队列准确率96%(95%CI [80-99%]),敏感度83%,特异度100%。
  • 未使用ComBat harmonization时,DFS和LRC模型准确率分别显著降低至82-85%和71-86%。
  • 使用标准临床变量的最佳预测准确率仅为56-60%。

关键数值与推荐

  • DFS模型使用ADC MRI的一个影像组学特征;LRC模型在DFS模型基础上增加一个PET影像组学特征。

临床怎么用

  • 该模型可用于局部晚期宫颈癌患者放化疗后复发风险预测,辅助临床决策。
  • 需在更大规模前瞻性研究中进一步确认基于该模型的患者管理流程图。

局限性

  • 样本量有限(验证队列分别为50和28例)。
  • 需未来更大规模前瞻性研究确认。

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: The aim of this study was to validate previously developed radiomics models relying on just two radiomics features from 18F-fluorodeoxyglucose positron emission tomography (PET) and magnetic resonance imaging (MRI) images for prediction of disease free survival (DFS) and locoregional control (LRC) in locally advanced cervical cancer (LACC). METHODS: Patients with LACC receiving chemoradiotherapy were enrolled in two French and one Canadian center. Pre-treatment imaging was performed for each patient. Multicentric harmonization of the two radiomics features was performed with the ComBat method. The models for DFS (using the feature from apparent diffusion coefficient (ADC) MRI) and LRC (adding one PET feature to the DFS model) were tuned using one of the French cohorts (n = 112) and applied to the other French (n = 50) and the Canadian (n = 28) external validation cohorts. RESULTS: The DFS model reached an accuracy of 90% (95% CI [79-98%]) (sensitivity 92-93%, specificity 87-89%) in both the French and the Canadian cohorts. The LRC model reached an accuracy of 98% (95% CI [90-99%]) (sensitivity 86%, specificity 100%) in the French cohort and 96% (95% CI [80-99%]) (sensitivity 83%, specificity 100%) in the Canadian cohort. Accuracy was significantly lower without ComBat harmonization (82-85% and 71-86% for DFS and LRC, respectively). The best prediction using standard clinical variables was 56-60% only. CONCLUSIONS: The previously developed PET/MRI radiomics predictive models were successfully validated in two independent external cohorts. A proposed flowchart for improved management of patients based on these models should now be confirmed in future larger prospective studies.

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, Visvikis D, Vallières M, et al. External validation of a combined PET and MRI radiomics model for prediction of recurrence in cervical cancer patients treated with chemoradiotherapy. Eur J Nucl Med Mol Imaging. 2018. PMID: 30535746. doi:10.1007/s00259-018-4231-9

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。