基于临床及CT放射组学特征鉴别非典型肺错构瘤与肺腺癌  

Discriminate atypical pulmonary hamartoma from lung adenocarcinoma based on clinical and CT radiomics features

作　　者：王传彬 李翠平 曹锋 董江宁 吴兴旺[1] WANG Chuanbin;LI Cuiping;CAO Feng;DONG Jiangning;WU Xingwang(Department of Radiology,the First Affiliated Hospital of Anhui Medical University,Hefei 230022,China;Department of Radiology,the First Affiliated Hospital of USTC,Division of Life Sciences and Medicine,University of Science and Technology of China,Hefei 230031,China)

机构地区：[1]安徽医科大学第一附属医院放射科,安徽合肥230022 [2]中国科学技术大学附属第一医院(安徽省立医院)西区放射科,安徽合肥230031

出　　处：《实用放射学杂志》2024年第8期1238-1242,共5页Journal of Practical Radiology

基　　金：安徽省自然科学基金面上项目(2308085MH241)。

摘　　要：目的探讨基于临床及CT放射组学特征构建的联合预测模型鉴别非典型肺错构瘤(APH)和非典型肺腺癌(ALA)的价值。方法回顾性选取经病理证实的APH和ALA患者290例。安徽医科大学第一附属医院的250例患者按照7︰3的比例随机分为训练集(APH 91例,ALA 84例)和内部验证集(APH 39例,ALA 36例),中国科学技术大学附属第一医院的40例患者作为外部验证集(APH 21例,ALA 19例)。利用筛选出的临床-CT特征和放射组学特征分别构建独立模型及多因素logistic回归联合模型,并绘制列线图。采用受试者工作特征(ROC)曲线和DeLong检验对模型的性能进行评价与比较。结果利用3个临床-CT特征和4个放射组学特征建立的联合模型在训练集中的曲线下面积(AUC)为0.980,均高于临床-CT模型(AUC=0.885,P<0.001)及放射组学模型(AUC=0.975,P=0.042)。联合模型在内部验证集和外部验证集的AUC(0.963 vs 0.917)分别高于临床-CT模型(0.858 vs 0.774)及放射组学模型(0.953 vs 0.897)。结论基于临床及CT放射组学特征构建的联合预测模型能够提高对APH和ALA的鉴别诊断能力。Objective To explore the value of combined prediction model based on clinical and CT radiomics features in discriminating atypical pulmonary hamartoma(APH)from atypical lung adenocarcinoma(ALA).Methods A total of 290 patients with APH and ALA confirmed by pathology were retrospectively selected.250 patients from the First Affiliated Hospital of Anhui Medical University were randomly assigned into a training set(APH=91,ALA=84)and an internal validation set(APH=39,ALA=36)at a ratio of 7︰3,and other 40 patients from the First Affiliated Hospital of USTC were assigned as an external validation set(APH=21,ALA=19).The independent model and multivariate logistic regression combined model were constructed using the selected clinical-CT features and radiomics features,respectively,and a nomogram was drawn.Receiver operating characteristic(ROC)curve and DeLong test were used to evaluate and compare the performances of the models.Results The area under the curve(AUC)of the combined model established by 3 clinical-CT features and 4 radiomics features in the training set was 0.980,which was higher than that of clinical-CT model(AUC=0.885,P<0.001)and radiomics model(AUC=0.975,P=0.042).The AUC of the combined model in the internal and external validation sets(0.963 vs 0.917)were also higher than those of clinical-CT model(0.858 vs 0.774)and radiomics model(0.953 vs 0.897),respectively.Conclusion The combined prediction model based on clinical and CT radiomics features can improve the differential diagnosis ability of APH and ALA.

关 键 词：错构瘤 肺腺癌 放射组学 列线图 计算机体层成像 

分 类 号：R734.2[医药卫生—肿瘤] R445[医药卫生—临床医学] R814.42