Department of Nuclear Medicine, West China Hospital, Sichuan University, Chengdu, Sichuan, China.
Department of Oncology, West China Hospital, Sichuan University, No. 37, Lane Guoxue Wuhou District, Chengdu City, Sichuan Province, China.
Eur Radiol. 2020 Oct;30(10):5578-5587. doi: 10.1007/s00330-020-06943-1. Epub 2020 May 20.
To identify an F-fluorodeoxyglucose (F-FDG) positron emission tomography (PET) radiomics-based model for predicting progression-free survival (PFS) and overall survival (OS) of nasal-type extranodal natural killer/T cell lymphoma (ENKTL).
In this retrospective study, a total of 110 ENKTL patients were divided into a training cohort (n = 82) and a validation cohort (n = 28). Forty-one features were extracted from pretreatment PET images of the patients. Least absolute shrinkage and selection operator (LASSO) regression was used to develop the radiomic signatures (R-signatures). A radiomics-based model was built and validated in the two cohorts and compared with a metabolism-based model.
The R-signatures were constructed with moderate predictive ability in the training and validation cohorts (R-signature: AUC = 0.788 and 0.473; R-signature: AUC = 0.637 and 0.730). For PFS, the radiomics-based model showed better discrimination than the metabolism-based model in the training cohort (C-index = 0.811 vs. 0.751) but poorer discrimination in the validation cohort (C-index = 0.588 vs. 0.693). The calibration of the radiomics-based model was poorer than that of the metabolism-based model (training cohort: p = 0.415 vs. 0.428, validation cohort: p = 0.228 vs. 0.652). For OS, the performance of the radiomics-based model was poorer (training cohort: C-index = 0.818 vs. 0.828, p = 0.853 vs. 0.885; validation cohort: C-index = 0.628 vs. 0.753, p < 0.05 vs. 0.913).
Radiomic features derived from PET images can predict the outcomes of patients with ENKTL, but the performance of the radiomics-based model was inferior to that of the metabolism-based model.
• The R-signatures calculated by using F-FDG PET radiomic features can predict the survival of patients with ENKTL. • The radiomics-based models integrating the R-signatures and clinical factors achieved good predictive values. • The performance of the radiomics-based model was inferior to that of the metabolism-based model in the two cohorts.
确定基于 F-氟代脱氧葡萄糖（F-FDG）正电子发射断层扫描（PET）放射组学的模型，用于预测鼻型结外自然杀伤/T 细胞淋巴瘤（ENKTL）的无进展生存期（PFS）和总生存期（OS）。
在这项回顾性研究中，共纳入 110 例 ENKTL 患者，分为训练队列（n=82）和验证队列（n=28）。从患者的预处理 PET 图像中提取了 41 个特征。使用最小绝对收缩和选择算子（LASSO）回归来开发放射组学特征（R 特征）。在两个队列中建立和验证了基于放射组学的模型，并与基于代谢的模型进行了比较。
R 特征在训练和验证队列中具有中等预测能力（R 特征：AUC=0.788 和 0.473；R 特征：AUC=0.637 和 0.730）。对于 PFS，基于放射组学的模型在训练队列中的区分能力优于基于代谢的模型（C 指数=0.811 比 0.751），但在验证队列中的区分能力较差（C 指数=0.588 比 0.693）。基于放射组学的模型的校准能力不如基于代谢的模型（训练队列：p=0.415 比 0.428，验证队列：p=0.228 比 0.652）。对于 OS，基于放射组学的模型的性能较差（训练队列：C 指数=0.818 比 0.828，p=0.853 比 0.885；验证队列：C 指数=0.628 比 0.753，p<0.05 比 0.913）。
源自 PET 图像的放射组学特征可预测 ENKTL 患者的结局，但基于放射组学的模型的性能逊于基于代谢的模型。
