Esposito Fabiana, Manco Luigi, Manenti Guglielmo, Pupo Livio, Nunzi Andrea, Laureana Roberta, Guarnera Luca, Marinoni Massimiliano, Buzzatti Elisa, Gigliotti Paola Elda, Micillo Andrea, Scribano Giovanni, Venditti Adriano, Postorino Massimiliano, Del Principe Maria Ilaria
Hematology, Department of Biomedicine and Prevention, University of Roma Tor Vergata, 00133 Rome, Italy.
Medical Physics Unit, University Hospital of Ferrara, 44124 Ferrara, Italy.
Diagnostics (Basel). 2025 May 19;15(10):1281. doi: 10.3390/diagnostics15101281.
The role of PET/CT imaging in chronic lymphoproliferative syndromes (CLL) is debated. This study examines the potential of PET/CT radiomics in predicting outcomes and genetic profiles in CLL patients. A retrospective analysis was conducted on 50 CLL patients treated at Policlinico Tor Vergata, Rome, and screened, at diagnosis, with [F]-FDG PET/CT. Potentially pathological lymph nodes were semi-automatically segmented. Genetic mutations in , , and were assessed. Eight hundred and sixty-five radiomic features were extracted, with the cohort split into training (70%) and validation (30%) sets. Four machine learning models, each with Random Forest, Stochastic Gradient Descent, and Support Vector Machine learners, were trained. Progression occurred in 10 patients. The selected radiomic features from CT and PET datasets were correlated with four models of progression and mutations (, , ). The Random Forest models outperformed others in predicting progression (AUC = 0.94/0.88, CA = 0.87/0.75, TP = 80.00%/87.50%, TN = 72.70%/87.50%) and the occurrence of (AUC = 0.94/0.96, CA = 0.87/0.80, TP = 87.50%/90.21%, TN = 85.70%/90.90%), and (AUC = 0.94/0.85, CA = 0.87/0.67, TP = 80.00%/88.90%, TN = 80.00%/83.30%)mutations. The IGVH models showed poorer performance. ML models based on PET/CT radiomic features effectively predict outcomes and genetic profiles in CLL patients.
正电子发射断层扫描/计算机断层扫描（PET/CT）成像在慢性淋巴细胞增殖性综合征（CLL）中的作用存在争议。本研究探讨了PET/CT放射组学在预测CLL患者预后和基因谱方面的潜力。对罗马托尔韦尔加塔大学综合医院治疗的50例CLL患者进行了回顾性分析，这些患者在诊断时接受了[F]-FDG PET/CT检查。对潜在的病理性淋巴结进行半自动分割。评估了 、 和 中的基因突变。提取了865个放射组学特征，并将队列分为训练集（70%）和验证集（30%）。训练了四个机器学习模型，每个模型都有随机森林、随机梯度下降和支持向量机学习器。10例患者出现疾病进展。从CT和PET数据集中选择的放射组学特征与四种进展和突变模型（ 、 、 ）相关。随机森林模型在预测进展（AUC = 0.94/0.88，CA = 0.87/0.75，TP = 80.00%/87.50%，TN = 72.70%/87.50%）以及 （AUC = 0.94/0.96，CA = 0.87/0.80，TP = 87.50%/90.21%，TN = 85.70%/90.90%）和 （AUC = 0.94/0.85，CA = 0.87/0.67，TP = 80.00%/88.90%，TN = 80.00%/83.30%）突变的发生方面优于其他模型。免疫球蛋白重链可变区（IGVH）模型表现较差。基于PET/CT放射组学特征的机器学习模型能够有效预测CLL患者的预后和基因谱。
