Jing Fenglian, Zhang Xinchao, Liu Yunuan, Chen Xiaolin, Zhao Xinming, Chen Xiaoshan, Yuan Huiqing, Dai Meng, Wang Na, Han Jingya, Zhang Jingmian
Department of Nuclear Medicine, The Fourth Hospital of Hebei Medical University, Shijiazhuang, People's Republic of China.
Department of Nuclear Medicine, Hebei General Hospital, Shijiazhuang, People's Republic of China.
Cancer Biother Radiopharm. 2025 Mar;40(2):114-121. doi: 10.1089/cbr.2024.0115. Epub 2024 Sep 4.
This study aimed to predict therapeutic efficacy among diffuse large B-cell lymphoma (DLBCL) after R-CHOP (-like) therapy using baseline F-fluorodeoxyglucose positron emission tomography (F-FDG PET) radiomics. A total of 239 patients with DLBCL were enrolled in this study, with 82 patients having refractory/relapsed disease. The radiomics signatures were developed using a stacking ensemble approach. The efficacy of the radiomics signatures, the National Comprehensive Cancer Network-International Prognostic Index (NCCN-IPI), conventional PET parameters model, and their combinations in assessing refractory/relapse risk were evaluated using receiver operating characteristic (ROC) curves, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy and decision curve analysis. The stacking model, along with the integrated model that combines stacking with the NCCN-IPI and SD (the distance between the two lesions farthest apart, normalized to the patient's body surface area), showed remarkable predictive capabilities with a high area under the curve (AUC), sensitivity, specificity, PPV, NPV, accuracy, and significant net benefit of the AUC (NB-AUC). Although no significant differences were observed between the combined and stacking models in terms of the AUC in either the training cohort (AUC: 0.992 vs. 0.985, = 0.139) or the testing cohort (AUC: 0.768 vs. 0.781, = 0.668), the integrated model exhibited higher values for sensitivity, PPV, NPV, accuracy, and NB-AUC than the stacking model. Baseline PET radiomics could predict therapeutic efficacy in DLBCL after R-CHOP (-like) therapy, with improved predictive performance when incorporating clinical features and SD.
本研究旨在使用基线氟脱氧葡萄糖正电子发射断层扫描（F-FDG PET）影像组学预测弥漫性大B细胞淋巴瘤（DLBCL）患者接受R-CHOP（类）治疗后的疗效。本研究共纳入239例DLBCL患者，其中82例为难治性/复发性疾病。影像组学特征采用堆叠集成方法构建。使用受试者工作特征（ROC）曲线、敏感性、特异性、阳性预测值（PPV）、阴性预测值（NPV）、准确性和决策曲线分析评估影像组学特征、美国国立综合癌症网络国际预后指数（NCCN-IPI）、传统PET参数模型及其组合在评估难治性/复发风险方面的疗效。堆叠模型以及将堆叠与NCCN-IPI和SD（两个最远病变之间的距离，根据患者体表面积进行归一化）相结合的综合模型显示出显著的预测能力，曲线下面积（AUC）、敏感性、特异性、PPV、NPV、准确性均较高，且AUC的显著净效益（NB-AUC）较高。尽管在训练队列（AUC：0.992对0.985，P = 0.139）或测试队列（AUC：0.768对0.781，P = 0.668）中，联合模型和堆叠模型在AUC方面未观察到显著差异，但综合模型在敏感性、PPV、NPV、准确性和NB-AUC方面的值均高于堆叠模型。基线PET影像组学可以预测DLBCL患者接受R-CHOP（类）治疗后的疗效，纳入临床特征和SD后预测性能有所提高。
