文献速递肿瘤 PET/CT核素与放射性配体治疗

术前[18F]FDG PET原发肿瘤影像组学预测子宫内膜癌侵袭性疾病及不良结局

Predicting aggressive disease and poor outcome in endometrial cancer using preoperative [18F]FDG PET primary tumor radiomics.
PubMed 文献 · Eur J Nucl Med Mol Imaging · 2025-06-11

在489例子宫内膜癌患者中,利用术前[18F]FDG PET原发肿瘤影像组学特征构建DSS评分(Rdss)及联合模型(Cdss),并与常规PET指标比较。测试集中Rdss预测2年和5年DSS的AUC分别为0.855和0.720,优于SUVmax和SUVmean,但与MTV、TLG和LNPET相似;Cdss预测2年和5年DSS的AUC分别为0.909和0.817,优于所有常规影像标志物(MTV除外,2年时P=0.29)。

要点

  • 测试集中Rdss预测2年、5年DSS的AUC为0.855、0.720,优于SUVmax和SUVmean,但与MTV、TLG、LNPET相似。
  • Cdss预测2年DSS的AUC为0.909,优于除MTV外的所有常规影像标志物(MTV P=0.29)。
  • Cdss预测5年DSS的AUC为0.817,优于所有常规影像标志物(包括MTV,AUC≤0.696,P≤0.05)。

核心结论

  • Rdss能高精度预测短期生存,优于肿瘤SUVmax/SUVmean,但不优于MTV、TLG和LNPET。
  • 联合Cdss模型对短期和长期生存预测均具有高精度,优于所有常规PET影像标志物。

研究设计与样本

  • 回顾性分析489例子宫内膜癌患者术前[18F]FDG PET影像,以SUV阈值>2.5定义原发代谢肿瘤体积(MTV)。
  • 由第二阅片者在154/489例患者中提取特征并计算组内相关系数(ICC),保留ICC>0.75的特征,并应用ComBat协调减少扫描仪/协议对提取特征的影响。
  • 患者分为训练集(n=343)和测试集(n=146),在训练集中采用LASSO Cox回归构建影像组学DSS评分(Rdss),并采用多变量Cox风险分析构建包含Rdss、PET阳性淋巴结(LNPET)和术前组织学风险的联合模型(Cdss)。
  • 通过比较时间依赖ROC曲线下面积(tdROC AUC)评估Rdss、Cdss与常规PET标志物(SUVmax、SUVmean、MTV、肿瘤病灶糖酵解TLG和LNPET)的预测性能。

主要发现

  • 测试集中,Rdss预测2年和5年DSS的AUC分别为0.855和0.720,高于SUVmax(0.548、0.572)和SUVmean(0.549、0.554)(所有P≤0.04),但与MTV(0.863、0.696)、TLG(0.814、0.672)和LNPET(0.802、0.626)相似(所有P≥0.12)。
  • 测试集中,Cdss预测2年DSS的AUC为0.909,优于所有常规影像标志物(所有P≤0.04),但MTV除外(P=0.29)。
  • 测试集中,Cdss预测5年DSS的AUC为0.817,优于所有常规影像标志物,包括MTV(AUC≤0.696,所有P≤0.05)。

关键数值与推荐

  • 以SUV阈值>2.5定义原发代谢肿瘤体积(MTV)。
  • 影像组学特征保留标准为ICC>0.75。
  • 训练集n=343,测试集n=146;第二阅片者提取特征的患者数为154/489。

局限性

  • 原文未报告局限性。

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 a [18F]fluorodeoxyglucose ([18F]FDG) positron emission tomography (PET) primary tumor radiomic model for predicting disease-specific survival (DSS), and compare it with conventional PET markers in a large endometrial cancer cohort. METHODS: Radiomic features were extracted from preoperative [18F]FDG PET scans of 489 endometrial cancer patients using a standardized uptake value (SUV) threshold > 2.5 to define primary metabolic tumor volumes (MTVs). A second reader extracted features in 154/489 patients, in which intraclass correlation coefficients (ICCs) were calculated. Radiomic features with ICCs > 0.75 were retained and ComBat harmonization was applied to reduce scanner/protocol effects on the extracted features. Patients were divided into training (n = 343) and test (n = 146) sets. A radiomic DSS score (Rdss) was developed in the training set using least absolute shrinkage and selection operator (LASSO) Cox regression. A combined model (Cdss), incorporating Rdss, PET positive lymph nodes (LNPET) and preoperative histology risk was constructed using multivariable Cox hazard analyses. Prediction performances were assessed by comparing areas under time-dependent receiver operating characteristic curves (tdROCs AUCs) for Rdss, Cdss, and conventional PET markers: SUVmax, SUVmean, MTV, tumor lesion glycolysis (TLG) and LNPET. RESULTS: In the test set, AUCs for 2- and 5-year DSS were higher for Rdss (0.855, 0.720) compared to SUVmax (0.548, 0.572) and SUVmean (0.549, 0.554) (p ≤ 0.04 for all), while similar to MTV (0.863, 0.696), TLG (0.814, 0.672) and LNPET (0.802, 0.626) (p ≥ 0.12 for all). Cdss predicted 2-year DSS with AUC of 0.909 in the test set, outperforming all conventional imaging markers (p ≤ 0.04 for all) except MTV (p = 0.29). For 5-year DSS, Cdss (AUC: 0.817) outperformed all conventional imaging markers, including MTV (AUC ≤ 0.696, p ≤ 0.05, for all). CONCLUSION: Rdss predicts short-term survival with high accuracy, outperforming tumor SUVmax/mean, but not MTV, TLG and LNPET. The combined Cdss model yields high accuracy for predicting both short- and long-term survival, outperforming all conventional PET imaging markers.

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

引用

  1. Fasmer KE, Gulati A, Lindås S, et al. Predicting aggressive disease and poor outcome in endometrial cancer using preoperative [18F]FDG PET primary tumor radiomics. Eur J Nucl Med Mol Imaging. 2025. PMID: 40498156. doi:10.1007/s00259-025-07335-7

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。