基于临床、能谱CT及CT影像组学特征构建机器学习模型术前预测结直肠癌患者KRAS基因状态  

Machine Learning Model Based on Clinical,CT Spectral and CT Radiomics Features for Predicting KRAS Gene Status in Colorectal Cancer Patients Before Surgery

作　　者：李泽茂 王雅静 周伟 王星稳 陈伟彬 LI Zemao;WANG Yajing;ZHOU Wei(Medical Imaging Centre,North China University of Science and Technology,Tangshan,Hebei Province 063000,P.R.China)

机构地区：[1]华北理工大学附属医院医学影像中心,唐山063000

出　　处：《临床放射学杂志》2024年第10期1737-1743,共7页Journal of Clinical Radiology

基　　金：2023年度唐山市人才资助项目(编号:C202303027)。

摘　　要：目的探讨基于临床、能谱CT及CT影像组学特征构建的不同机器学习模型对术前预测结直肠癌(CRC)患者Kirsten大鼠肉瘤病毒癌基因同源物(KRAS)基因状态的应用价值。方法回顾性搜集2020年6月至2023年12月经病理确诊为结直肠腺癌204例。依据KRAS基因检测结果分为KRAS野生型组(n=87)和KRAS突变型组(n=117)。于CT静脉期薄层增强图像勾画病灶感兴趣区(ROI),提取影像组学特征,按照7∶3比例随机划分为训练集和测试集,采用最小绝对收缩与选择算子(LASSO)算法筛选影像组学特征。由支持向量机(SVM)、极端梯度提升(XGBoost)及逻辑回归(LR)机器学习算法构建术前预测CRC患者KRAS基因亚型的模型(共六种,组学数据构建的SVM模型,XGBoost模型及LR模型;临床、能谱CT-CT影像组学联合数据构建的SVM模型,XGBoost模型及LR模型),绘制受试者工作特征(ROC)曲线,计算曲线下面积(AUC),评价各模型预测CRC患者KRAS基因亚型的效能;以DeLong检验比较各模型间效能差异。以决策曲线分析(DCA)评价临床、能谱CT及CT影像组学联合数据构建的三种机器学习模型临床应用价值。结果KRAS野生型组和KRAS突变型组间静脉期能谱参数碘基值(IC)、标准化碘基值(NIC)及有效原子序数(Eff-Z)具有统计学差异(P<0.05);年龄、性别及血清肿瘤标志物等临床指标均无显著差异(P>0.05)。相较于单纯CT影像组学数据,联合静脉期能谱参数后进一步提高了模型的预测效能,由CT影像组学数据及能谱CT-CT影像组学联合数据构建的SVM模型AUC值分别为0.810,0.866;准确率分别为0.758,0.790。由CT影像组学数据及能谱CT-CT影像组学联合数据构建的XGBoost模型AUC值分别为0.804,0.918;准确率分别为0.790,0.855。由CT影像组学数据及能谱CT-CT影像组学联合数据构建的LR模型AUC值分别为0.827,0.910;准确率分别为0.774,0.806。其中,能谱CT-CT影像组学联合数据构建的XGBoost模型的AUC值、�Objective To explore the application value of different machine learning models to predict preoperative KRAS gene status in patients with colorectal cancer based on clinical,CT spectral and CT radiomics features.Methods From June 2020 to December 2023,a retrospective study was performed for the two hundred and four patients with colorectal adenocarcinoma through pathology confrmed in North China University of Science and Technology Affiliated Hospital.Based on KRAS gene test results,these cases were divided into the KRAS wild type(n=87)and KRAS mutant type(n=117)groups.The regions of interest of colorectal cancer were drawn on the venous enhancement thin images,and all radiomics features were further extracted.Randomly divided into the training group and the test group at a ratio of 7∶3,and the least absolute shrinkage and selection operator(LASSO)was used to screen the radiomics features.Support vector machine(SVM),eXtreme Gradient Boosting(XGBoost)and Logistic regression(LR)were constructed to predict KRAS gene subtype in colorectal cancer patients before surgery(a total of 6,SVM model,XGBoost model and LR model were constructed from the pure radiomics features;SVM model,XGBoost model and LR model were constructed from the combination of clinical,CT spectral and CT radiomics features).The receiver operating characteristic(ROC)curve was drawn,and the area under the curve(AUC)was calculated to evaluate the effectiveness of each model for predicting the KRAS gene subtype of colorectal cancer.Delong test was used to compare the effectiveness among 6 models.The clinical application value of the three machine learning models based on the combination of clinical,CT spectral and CT radiomics features were evaluated with decision curve analysis(DCA).Results The differences in the Iodine concentration(IC),Normalized iodine concentration(NIC)and Effective-Z(Eff-Z)of the venous phase energy spectral parameters were statistically significant between the wild-type KRAS and mutant KRAS groups(P<0.05);The two groups showed n

关 键 词：结直肠癌 影像组学 CT能谱成像 KRAS基因 机器学习 

分 类 号：R735.34[医药卫生—肿瘤]