多模态磁共振成像检查影像组学模型对直肠癌微卫星不稳定性的预测价值  

Predictive value of multimodal magnetic resonance imaging based radiomics model for microsatellite instability of rectal cancer

作　　者：金京 王华[2] 陈义林 Jin Jing;Wang Hua;Chen Yilin(Department of Imaging,Ningbo Urology&Nephrology Hospital(Ningbo Yinzhou No.2 Hospital),Ningbo 315192,Zhejiang Province,China;Department of Radiology,the First Affiliated Hospital of Zhejiang University School of Medicine,Hangzhou 310003,China)

机构地区：[1]宁波市泌尿肾病医院(鄞州区第二医院)医学影像科,宁波315192 [2]浙江大学医学院附属第一医院放射科,杭州310003

出　　处：《中华消化外科杂志》2023年第6期779-787,共9页Chinese Journal of Digestive Surgery

基　　金：浙江省医药卫生科技项目(2020KY896)。

摘　　要：目的探讨多模态磁共振成像(MRI)检查影像组学模型对直肠癌微卫星不稳定性(MSI)的预测价值。方法采用回顾性队列研究方法。收集2020年1月至2022年12月2家医学中心收治的117例(宁波市泌尿肾病医院74例、浙江大学医学院附属第一医院43例)直肠癌患者的临床病理资料;男73例,女44例;年龄为(63±5)岁。117例患者通过随机数字表法以7∶3随机分为训练集70例和测试集47例。117例患者均行盆腔MRI检查。观察指标:(1)影像组学预测模型构建及特征分析。(2)影响训练集直肠癌MSI的因素分析。(3)直肠癌MSI预测模型的构建与评价。正态分布的计量资料以x±s表示,组间比较采用t检验;偏态分布的计量资料以M(Q1,Q3)表示,组间比较采用Mann⁃Whitney U检验;计数资料以绝对数表示,组间比较采用χ^(2)检验。单因素分析采用单因素方差分析,多因素分析采用Logistic回归模型前进法。绘制受试者工作特征(ROC)曲线,以曲线下面积(AUC)、决策曲线、校准曲线、Delong检验评价预测模型的效能。结果(1)影像组学预测模型构建及特征分析。提取117例患者5580个影像组学特征,经最大相关最小冗余筛选和最小化绝对收缩和选择算子回归模型降维后,最终筛选出9个影像组学特征。计算影像组学评分(R⁃score),构建基于R⁃score的影像组学预测模型。(2)影响训练集直肠癌MSI的因素分析。多因素分析结果显示:血小板计数是直肠癌患者MSI的独立影响因素[优势比=1.13,95%可信区间(CI)为1.06~1.21,P<0.05]。(3)直肠癌MSI预测模型的构建与评价。根据多因素分析结果构建临床特征预测模型、临床⁃影像组学联合预测模型。训练集中临床特征预测模型、影像组学预测模型、临床⁃影像组学联合预测模型的AUC分别为0.94(95%CI为0.86~0.98)、0.96(95%CI为0.88~0.99)、0.99(95%CI为0.93~1.00),灵敏度分别为90.7%、91.2%、96.9%,特异度分别为85.0%、88.Objective To investigate the predictive value of multimodal magnetic resonance imaging(MRI)based radiomics model for microsatellite instability(MSI)of rectal cancer.Methods The retrospective cohort study was conducted.The clinicopathological data of 117 patients with rectal cancer who were admitted to 2 medical centers,including 74 in Ningbo Urology&Nephrology Hospital and 43 in the First Affiliated Hospital of Zhejiang University School of Medicine,from January 2020 to December 2022 were collected.There were 73 males and 44 females,aged(63±5)years.Based on random number table,all 117 patients were divided into the training dataset of 70 cases and the test dataset of 47 cases with a ratio of 7:3.All patients underwent pelvic MRI examination.Observation indicators:(1)construction of radiomics prediction model and analysis of characteristics;(2)analysis of factors influencing MSI of rectal cancer in the training dataset;(3)construction and evaluation of the prediction model for MSI of rectal cancer.Measurement data with normal distribution were represented as Mean±SD,and comparison between groups was conducted using the t test.Measurement data with skewed distribution were represented as M(Q1,Q3),and comparison between groups was conducted using the Mann-Whitney U test.Count data were described as absolute numbers,and comparison between groups was conducted using the chi-square test.Univariate analysis was conducted using the one way ANOVA and multivariate analysis was conducted using the Logistic regression model with forward method.The receiver operating characteristic curve was drawn,and the area under the curve(AUC),decision curve,calibration curve and Delong test were used to evaluate the predictive ability of prediction model.Results(1)Construction of radiomics prediction model and analysis of characteristics.Five thousand five hundred and eighty radiomics features were finally extracted from the 117 patients.Based on the feature selection using the maximum correlation minimum redundancy method,and the leas

关 键 词：直肠肿瘤 微卫星不稳定性 影像组学 磁共振成像 预测 

分 类 号：R445.2[医药卫生—影像医学与核医学] R735.37[医药卫生—诊断学]