基于^(18)F-FDG PET/CT原发灶影像组学的联合模型预测NSCLC淋巴结转移的价值  

Predictive value of a combined model for lymph node metastasis in NSCLC based on primary lesion radiomics from^(18)F-FDG PET/CT

作　　者：来瑞鹤 滕月 戎剑 盛丹丹[3] 耿羽智 陈建新[2] 蒋冲 丁重阳 周正扬[6] Lai Ruihe;Teng Yue;Rong Jian;Sheng Dandan;Geng Yuzhi;Chen Jianxin;Jiang Chong;Ding Chongyang;Zhou Zhengyang(Department of Nuclear Medicine,Nanjing Drum Tower Hospital,Clinical Medical School of Nanjing Medical University,Nanjing 210008,China;Key Laboratory of Broadband Wireless Communication and Sensor Network Technology(Ministry of Education),School of Communications and Information Engineering,Nanjing University of Posts and Telecommunications,Nanjing 210003,China;Department of Nuclear Medicine,Second Affiliated Hospital of Nanjing Medical University,Nanjing 210011,China;Department of Nuclear Medicine,West China Hospital of Sichuan University,Chengdu 610041,China;Department of Nuclear Medicine,First Affiliated Hospital with Nanjing Medical University,Jiangsu Province Hospital,Nanjing 210029,China;Department of Radiology,Nanjing Drum Tower Hospital,Clinical Medical School of Nanjing Medical University,Nanjing 210008,China)

机构地区：[1]南京医科大学鼓楼临床医学院南京鼓楼医院核医学科,南京210008 [2]南京邮电大学通信与信息工程学院宽带无线通信与传感网技术重点实验室,南京210003 [3]南京医科大学第二附属医院核医学科,南京210011 [4]四川大学华西医院核医学科,成都610041 [5]南京医科大学附属第一医院江苏省人民医院核医学科,南京210029 [6]南京医科大学鼓楼临床医学院南京鼓楼医院放射科,南京210008

出　　处：《国际肿瘤学杂志》2025年第3期144-151,共8页Journal of International Oncology

基　　金：南京市卫生科技发展专项资金(YKK24090)。

摘　　要：目的评估基于原发灶^(18)F-氟代脱氧葡萄糖(^(18)F-FDG)PET/CT影像组学联合模型预测非小细胞肺癌(NSCLC)淋巴结转移的价值。方法回顾性分析南京鼓楼医院2013年6月至2023年7月治疗前行PET/CT显像的203例NSCLC患者的临床资料。按照7∶3比例将患者随机分为训练集(n=142)和验证集(n=61)。在训练集中建立预测模型,在训练集和验证集中分别对模型进行预测效能评估和临床应用价值验证。通过3D-slicer软件获得原发灶传统PET/CT参数和PET/CT影像组学特征。采用最小绝对收缩与选择算子(LASSO)、随机森林和极端梯度提升进行特征提取。采用支持向量机构建影像组学标签影像组学评分(Radscore)。采用单因素、多因素logistic回归分析预测NSCLC患者淋巴结转移的影响因素并建立模型,采用受试者操作特征(ROC)曲线评估模型的预测效能,采用校准曲线和临床决策曲线(DCA)评估模型的临床应用价值。结果203例NSCLC患者中淋巴结转移116例,其中训练集64例、验证集52例。采用3种互补的经典机器学习方法进行特征筛选,最终分别得到10个影像组学特征。Radscore-PET的最佳阈值为0.43,Radscore-CT的最佳阈值为0.39。单因素分析显示,性别(OR=0.48,95%CI为0.24~0.95,P=0.036)、肿瘤标志物水平(OR=3.81,95%CI为1.84~7.91,P<0.001)、肿瘤长径(OR=2.56,95%CI为1.27~5.16,P=0.009)、肿瘤短径(OR=3.73,95%CI为1.75~7.92,P=0.001)、空泡征(OR=0.32,95%CI为0.12~0.86,P=0.024)、环形代谢(OR=3.67,95%CI为1.33~10.13,P=0.012)、最大标准化摄取值(SUV_(max))(OR=6.57,95%CI为3.03~14.25,P<0.001)、肿瘤代谢体积(MTV)(OR=2.91,95%CI为1.43~5.92,P=0.003)、病灶糖酵解总量(TLG)(OR=4.23,95%CI为2.08~8.59,P<0.001)、Radscore-PET(OR=21.93,95%CI为9.04~53.20,P<0.001)和Radscore-CT(OR=13.72,95%CI为6.12~30.76,P<0.001)均是预测NSCLC患者淋巴结转移的影响因素。多因素分析显示,肿瘤标志物水平(OR=2.55,95%CI为1.11~5.90,P=0.028)、空泡征(OR=0.26,9Objective To evaluate the value of a combined model based on primary lesion ^(18)F-fluorodeoxyglucose(^(18)F-FDG)PET/CT radiomics for predicting lymph node metastasis in non-small cell lung cancer(NSCLC).Methods A retrospective analysis was conducted on the clinical data of 203 NSCLC patients who underwent pre-treatment PET/CT imaging at Nanjing Drum Tower Hospital from June 2013 to July 2023.Patients were randomly assigned to the training set(n=142)and the validation set(n=61)at a ratio of 7∶3.A predictive model was developed in the training set,and its predictive performance and clinical application value were assessed in both the training and validation sets.Traditional PET/CT parameters and PET/CT radiomics features of the primary lesion were obtained by 3D-slicer software.Least absolute shrinkage and selection operator(LASSO),random forest,and extreme gradient boosting were performed to extract features.Support vector machine was used to construct a radiomics score(Radscore).Univariate and multivariate logistic regression analysis was used to predict the influencing factors of lymph node metastasis in NSCLC patients and to establish models.Predictive performance of the models was evaluated by receiver operator characteristic(ROC)curves and clinical application value was assessed by calibration curves and decision curve analysis(DCA).Results Among 203 NSCLC patients,116 had lymph node metastasis,with 64 cases in the training set and 52 cases in the validation set.Three complementary classical machine learning methods were used for feature screening,and finally 10 radiomics features were obtained.The optimal threshold for Radscore-PET was 0.43 and the optimal threshold for Radscore-CT was 0.39.Univariate analysis showed that,sex(OR=0.48,95%CI:0.24-0.95,P=0.036),tumor marker levels(OR=3.81,95%CI:1.84-7.91,P<0.001),long diameter of tumor(OR=2.56,95%CI:1.27-5.16,P=0.009),short diameter of tumor(OR=3.73,95%CI:1.75-7.92,P=0.001),vacuolar sign(OR=0.32,95%CI:0.12-0.86,P=0.024),ring-like metabolism(OR=3.67,95%CI:1.3

关 键 词：癌 非小细胞肺 正电子发射断层显像计算机体层摄影术 影像组学 淋巴结转移 

分 类 号：R734.2[医药卫生—肿瘤]