Esposito Fabiana, Manco Luigi, Urso Luca, Adamantiadis Sara, Scribano Giovanni, De Marchi Lucrezia, Venditti Adriano, Postorino Massimiliano, Urbano Nicoletta, Gafà Roberta, Cuneo Antonio, Chiaravalloti Agostino, Bartolomei Mirco, Filippi Luca
Hematology, Department of Biomedicine and Prevention, University of Rome "Tor Vergata", 00133 Rome, Italy.
Medical Physics Unit, University Hospital of Ferrara, Via Aldo Moro 8, 44124 Ferrara, Italy.
Cancers (Basel). 2025 May 30;17(11):1827. doi: 10.3390/cancers17111827.
This bi-centric pilot study investigates the predictive value of pre-treatment [F]FDG PET/CT radiomics for assessing therapy response in primary mediastinal B-cell lymphoma (PMBCL).
All PMBCL patients underwent PET/CT with [F]FDG between January 2011 and January 2022 at Policlinico Tor Vergata University Hospital of Rome (70% training and 30% internal validation cohort) and Sant'Anna University Hospital of Ferrara (external validation cohort). The Deauville score (DS) was used as a predictor of therapy response (DS1-DS3 vs. DS4/DS5). A total of 121 quantitative radiomics features (RFts) were extracted from manually segmented volumes of interest (VOIs) in PET and CT images, according to IBSI. ComBat harmonization was applied to correct the center variability of features, followed by class balancing with SMOTE. Two machine learning (ML) prediction models, the PET model and the CT model, were independently developed using robust RFts. For each ML model, two different algorithms were trained (i.e., Random Forest, RF, and Support Vector Machine, SVM) using 10-fold cross validation, tested on the internal/external validation set. Receiver operating characteristic (ROC) curves, area under the curve (AUC), classification accuracy (CA), precision (Prec), sensitivity (Sen), specificity (Spec), true positive (TP) scores, and true negative (TN) scores were computed.
The entire dataset was composed of 29 samples for the Rome cohort (23 from D1-D3 and 6 from D4/D5) and 9 samples for the Ferrara cohort (4 from D1-D3 and 5 from D4/D5). A total of 27 RFts were identified as robust for each imaging modality. Both the CT and PET models effectively predicted the Deauville score. The performance metrics of the best classifier (SVM) for the CT and PET models in external validation were AUC = 0.75/0.80, CA = 0.85/0.77, Prec = 0.97/0.67, Sen = 0.60/0.80, Spec = 0.98/0.75, TP = 75.0%/66.7%, and TN = 77.8%/85.7%, respectively.
ML models trained on [F]FDG PET/CT radiomic features in PMBLC patients could predict the Deauville score.
本双中心前瞻性研究探讨治疗前[F]FDG PET/CT影像组学对评估原发性纵隔B细胞淋巴瘤（PMBCL）治疗反应的预测价值。
2011年1月至2022年1月期间，所有PMBCL患者在罗马的托尔韦尔加塔大学综合医院（70%为训练队列，30%为内部验证队列）和费拉拉的圣安娜大学医院（外部验证队列）接受了[F]FDG PET/CT检查。使用多维尔评分（DS）作为治疗反应的预测指标（DS1-DS3与DS4/DS5）。根据国际生物医学影像标准倡议（IBSI），从PET和CT图像中手动分割的感兴趣体积（VOI）中提取了总共121个定量影像组学特征（RFts）。应用ComBat归一化方法校正中心变异性，随后使用合成少数过采样技术（SMOTE）进行类平衡。使用稳健的RFts独立开发了两种机器学习（ML）预测模型，即PET模型和CT模型。对于每个ML模型，使用10折交叉验证训练两种不同的算法（即随机森林，RF，和支持向量机，SVM），并在内部/外部验证集上进行测试。计算受试者工作特征（ROC）曲线、曲线下面积（AUC）、分类准确率（CA）、精确率（Prec）、灵敏度（Sen）、特异性（Spec）、真阳性（TP）分数和真阴性（TN）分数。
整个数据集包括罗马队列的29个样本（D1-D3组23个，D4/D5组6个）和费拉拉队列的9个样本（D1-D3组4个，D4/D5组5个）。每种成像方式共识别出27个稳健的RFts。CT和PET模型均能有效预测多维尔评分。外部验证中CT和PET模型最佳分类器（SVM）的性能指标分别为AUC = 0.75/0.80，CA = 0.85/0.77，Prec = 0.97/0.67，Sen = 0.60/0.80，Spec = 0.98/0.75，TP = 75.0%/66.7%，TN = 77.8%/85.7%。
基于PMBLC患者[F]FDG PET/CT影像组学特征训练的ML模型可以预测多维尔评分。
