Ahrari Shamimeh, Zaragori Timothée, Rozenblum Laura, Oster Julien, Imbert Laëtitia, Kas Aurélie, Verger Antoine
Université de Lorraine, IADI, INSERM, UMR 1254, F-54000 Nancy, France.
Sorbonne Université, AP-HP, Hôpitaux Universitaires Pitié-Salpêtrière Charles Foix, Service de Médecine Nucléaire and LIB, INSERM U1146, F-75013 Paris, France.
Biomedicines. 2021 Dec 16;9(12):1924. doi: 10.3390/biomedicines9121924.
This study evaluates the relevance of F-DOPA PET static and dynamic radiomics for differentiation of high-grade glioma (HGG) progression from treatment-related changes (TRC) by comparing diagnostic performances to the current PET imaging standard of care. Eighty-five patients with histologically confirmed HGG and investigated by dynamic F-FDOPA PET in two institutions were retrospectively selected. ElasticNet logistic regression, Random Forest and XGBoost machine models were trained with different sets of features-radiomics extracted from static tumor-to-background-ratio (TBR) parametric images, radiomics extracted from time-to-peak (TTP) parametric images, as well as combination of both-in order to discriminate glioma progression from TRC at 6 months from the PET scan. Diagnostic performances of the models were compared to a logistic regression model with TBR ± clinical features used as reference. Training was performed on data from the first center, while external validation was performed on data from the second center. Best radiomics models showed only slightly better performances than the reference model (respective AUCs of 0.834 vs. 0.792, < 0.001). Our current results show similar findings at the multicentric level using different machine learning models and report a marginal additional value for TBR static and TTP dynamic radiomics over the classical analysis based on TBR values.
本研究通过将诊断性能与当前PET成像标准治疗方法进行比较，评估F-DOPA PET静态和动态放射组学在区分高级别胶质瘤（HGG）进展与治疗相关变化（TRC）方面的相关性。回顾性选取了85例经组织学确诊为HGG并在两个机构接受动态F-FDOPA PET检查的患者。使用不同的特征集训练弹性网络逻辑回归、随机森林和XGBoost机器学习模型，这些特征集包括从静态肿瘤与背景比值（TBR）参数图像中提取的放射组学特征、从达峰时间（TTP）参数图像中提取的放射组学特征，以及两者的组合，以便在PET扫描后6个月区分胶质瘤进展与TRC。将这些模型的诊断性能与以TBR±临床特征作为参考的逻辑回归模型进行比较。在第一个中心的数据上进行训练，而在第二个中心的数据上进行外部验证。最佳放射组学模型的表现仅略优于参考模型（AUC分别为0.834和0.792，<0.001）。我们目前的结果在多中心层面使用不同的机器学习模型显示了类似的发现，并报告了基于TBR值的经典分析相比，TBR静态和TTP动态放射组学的边际附加值。
