Wang Fanghu, Chen Yang, Tan Xiaoyue, Han Xu, Lu Wantong, Lu Lijun, Yuan Hui, Jiang Lei
PET Center, Department of Nuclear Medicine, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences).
School of Biomedical Engineering, Southern Medical University.
Nucl Med Commun. 2025 Feb 1;46(2):162-170. doi: 10.1097/MNM.0000000000001925. Epub 2025 Jan 7.
The study aimed to assess the role of 18 F-fluorodeoxyglucose (FDG) PET/computed tomography (CT) radiomics combined with clinical features using machine learning (ML) in predicting sarcopenia and prognosis of patients with diffuse large B-cell lymphoma (DLBCL).
A total of 178 DLBCL patients (118 and 60 applied for training and test sets, respectively) who underwent pretreatment 18 F-FDG PET/CT were retrospectively enrolled. Clinical characteristics and PET/CT radiomics features were analyzed, and feature selection was performed using univariate logistic regression and correlation analysis. Sarcopenia prediction models were built by ML algorithms and evaluated. Besides, prognostic models were also developed, and their associations with progression-free survival (PFS) and overall survival (OS) were identified.
Fourteen features were finally selected to build sarcopenia prediction and prognosis models, including two clinical (maximum standard uptake value of muscle and BMI), nine PET (seven gray-level and two first-order), and three CT (three gray-level) radiomics features. Among sarcopenia prediction models, combined clinical-PET/CT radiomics features models outperformed other models; especially the support vector machine algorithm achieved the highest area under curve of 0.862, with the sensitivity, specificity, and accuracy of 79.2, 83.3, and 78.3% in the test set. Furthermore, the consistency index based on the prognostic models was 0.753 and 0.807 for PFS and OS, respectively. The enrolled patients were subsequently divided into high-risk and low-risk groups with significant differences, regardless of PFS or OS ( P < 0.05).
ML models incorporating clinical and PET/CT radiomics features could effectively predict the presence of sarcopenia and assess the prognosis in patients with DLBCL.
本研究旨在评估采用机器学习（ML）的18F-氟脱氧葡萄糖（FDG）PET/计算机断层扫描（CT）影像组学联合临床特征在预测弥漫性大B细胞淋巴瘤（DLBCL）患者肌肉减少症及预后中的作用。
回顾性纳入178例接受过预处理18F-FDG PET/CT检查的DLBCL患者（分别有118例和60例用于训练集和测试集）。分析临床特征和PET/CT影像组学特征，并采用单因素逻辑回归和相关性分析进行特征选择。通过ML算法构建肌肉减少症预测模型并进行评估。此外，还建立了预后模型，并确定其与无进展生存期（PFS）和总生存期（OS）的相关性。
最终选择了14个特征来构建肌肉减少症预测和预后模型，包括2个临床特征（肌肉最大标准摄取值和BMI）、9个PET特征（7个灰度特征和2个一阶特征）和3个CT特征（3个灰度特征）。在肌肉减少症预测模型中，临床-PET/CT影像组学联合特征模型优于其他模型；尤其是支持向量机算法的曲线下面积最高，达到0.862，在测试集中的敏感性、特异性和准确性分别为79.2%、83.3%和78.3%。此外，基于预后模型的一致性指数对于PFS和OS分别为0.753和0.807。随后将纳入的患者分为高风险组和低风险组，无论PFS还是OS均存在显著差异（P < 0.05）。
结合临床和PET/CT影像组学特征的ML模型能够有效预测DLBCL患者肌肉减少症的存在并评估其预后。
