联合含瘤周肿瘤全体积CT影像组学特征及临床相关独立预测因子列线图预测肺腺癌淋巴血管侵犯  

Nomogram based on CT radiomics features of gross peritumoral tumor volume and clinical relevant independent predictors for predicting lymphovascular invasion of lung adenocarcinoma

作　　者：陈巧玲 冯峰[1] 李曼曼 薛婷 彭慧 石健 朱兴华[2] 段绍峰 CHEN Qiaoling;FENG Feng;LI Manman;XUE Ting;PENG Hui;SHI Jian;ZHU Xinghua;DUAN Shaofeng(Department of Radiology,Affiliated Tumor Hospital of Nantong University,Nantong 226000,China;Department of Pathology,Affiliated Tumor Hospital of Nantong University,Nantong 226000,China;GE Healthcare,Shanghai 210000,China)

机构地区：[1]南通大学附属肿瘤医院放射科,江苏南通226000 [2]南通大学附属肿瘤医院病理科,江苏南通226000 [3]GE医疗,上海210000

出　　处：《中国医学影像技术》2022年第8期1181-1186,共6页Chinese Journal of Medical Imaging Technology

基　　金：南通市2021年度市级社会民生科技项目(MS22021047)。

摘　　要：目的观察基于含瘤周的肿瘤全体积(GPTV)CT影像组学特征及临床相关独立预测因子构建的联合模型列线图预测肺腺癌淋巴血管侵犯(LVI)的价值。方法回顾性分析142例经病理证实的肺腺癌患者,以7∶3比例将其随机分为训练集(n=100,40例LVI阳性、60例LVI阴性)和验证集(n=42,17例LVI阳性、25例LVI阴性)。以单因素分析及多因素logistic回归分析筛选肺腺癌LVI的临床相关独立预测因子,以之构建临床模型。分别基于肿瘤全体积(GTV)及含瘤周3mm、6mm、9mm的GPTV(GPTV_(3)、GPTV_(6)和GPTV_(9))的增强动脉期CT图提取并筛选最佳影像组学特征,构建影像组学模型,即GTV、GPTV_(3)、GPTV_(6)和GPTV_(9)模型并筛选最佳者;基于后者的影像组学评分和临床相关独立预测因子构建联合模型,绘制列线图进行可视化。以受试者工作特征(ROC)曲线评估各模型预测肺腺癌LVI的效能,以决策曲线分析(DCA)评价联合模型列线图的价值。结果性别、吸烟和毛刺征均为肺腺癌LVI的临床相关独立预测因子(P均<0.05)。分别基于GTV、GPTV_(3)、GPTV_(6)及GPTV_(9)筛选出7、16、10及8个最佳影像组学特征,用于构建GTV、GPTV_(3)、GPTV_(6)及GPTV_(9)模型。GPTV_(3)模型预测训练集、验证集肺腺癌LVI的曲线下面积(AUC)分别为0.82、0.77,均高于GTV(0.79、0.72,Z=3.74、2.62,P均<0.01)、GPTV_(6)(0.80、0.72,Z=2.40、2.06,P均<0.05)及GPTV_(9)(0.77,0.72,Z=3.03、2.59,P均<0.01),为最佳影像组学模型。联合模型列线图(0.86、0.73,Z=2.66、2.31,P均<0.05)及GPTV_(3)模型(0.82、0.77,Z=2.23、2.54,P均<0.05)于训练集和验证集的AUC均高于临床模型(0.73、0.61),而联合模型列线图与GPTV_(3)模型的AUC差异均无统计学意义(Z=1.57、0.88,P均>0.05)。阈值取0.20~0.50时,联合模型列线图与GPTV_(3)模型的净获益相当,且均大于临床模型。结论基于GPTV_(3)影像组学特征及临床相关独立预测因子的列线图可有效预测肺腺癌LVI。Objective To explore the value of the nomogram based on CT radiomics features gross peritumoral tumor volume(GPTV)and clinical relevant independent predictors for predicting lymphovascular invasion(LVI)of lung adenocarcinoma.Methods Data of 142 patients with pathologically confirmed lung adenocarcinoma were retrospectively analyzed.The patients were randomly divided into training set(n=100,including 40 LVI-positive and 60 LVI-negative ones)and validation set(n=42,including 17 LVI-positive and 25 LVI-negative)at the ratio of 7∶3.Univariate analysis and multivariate logistic regression analysis were used to select clinical relevant independent predictors for LVI of lung adenocarcinoma to construct the clinical model.Based on enhanced CT arterial phase images of gross tumor volume(GTV)and GPTV incorporating peritumoral 3 mm,6 mm and 9 mm regions(GPTV_(3),GPTV_(6) and GPTV_(9)),the best radiomics features were extracted and screened to construct radiomics models,including GTV,GPTV_(3),GPTV_(6) and GPTV_(9) models.Then the best radiomics model was selected.A combined model was constructed based on radiomics score of the best radiomics model and clinical relevant independent predictors,and a nomogram was drawn for visualization of the combined model.Receiver operating characteristic(ROC)curves were drawn to evaluate the efficacy of each model for predicting LVI of lung adenocarcinoma,and decision curve analysis(DCA)was used to assess the value of the combined model nomogram.Results Gender,smoking and spiculation were all clinically relevant independent predictors for LVI of lung adenocarcinoma(all P<0.05),and were used to establish the clinical model.Based on GTV,GPTV_(3),GPTV_(6) and GPTV_(9),7,16,10 and 8 optimal radiomics features were selected,respectively,and GTV,GPTV_(3),GPTV_(6) and GPTV_(9) models were constructed.The areas under the curve(AUC)of GPTV_(3) model for predicting LVI of lung adenocarcinoma in the training set and validation set was 0.82 and 0.77,respectively,all higher than those of GTV(0.79,0.72

关 键 词：肺肿瘤 体层摄影术 X线计算机 影像组学 淋巴血管侵犯 

分 类 号：R734.2[医药卫生—肿瘤] R814.42[医药卫生—临床医学]