基于DBT的影像组学对三阴性乳腺癌的预测价值  

Value of DBT⁃Based Radiomics in Predictiving Triple⁃Negative Breast Cancer

作　　者：武静[1,2] 马彦云[2] 黄静[1] 李彪 WU Jing;MA Yanyun;HUANG Jing(School of Medical Imaging,Shanxi Medical University,Taiyuan,Shanxi Province 030000,P.R.China)

机构地区：[1]山西医科大学医学影像学院,太原030000 [2]山西医科大学医学第一医院影像科,太原030000

出　　处：《临床放射学杂志》2024年第8期1292-1297,共6页Journal of Clinical Radiology

基　　金：2022年山西省高等学校教学改革创新项目(编号:J20220416);山西省重点研发计划项目(编号:201803D31100)。

摘　　要：目的探索基于数字乳腺断层摄影(DBT)图像的影像组学特征对术前预测三阴性乳腺癌(TNBC)的价值。方法回顾分析乳腺癌患者的DBT图像及临床资料,按纳入排除标准共纳入198例患者,按照病理结果分为非三阴性乳腺癌(NTNBC)146例和TNBC 52例。利用3D Slicer软件勾画感兴趣区(ROI),Python提取影像组学特征,并用t检验及最小绝对收缩和选择算子(LASSO)算法筛选特征,对临床及影像特征采用单因素分析进行筛选。通过支持向量机(SVM)分类器构建模型,利用曲线下面积(AUC)等指标评估模型预测效能,并用Delong检验对各个模型的AUC进行比较。结果最终选择初潮年龄、肿块伴钙化及乳腺影像报告和数据系统(BI⁃RADS)分级(P<0.05)建立临床及影像模型,选取4个重要的影像组学特征建立影像组学模型,并将两组特征相结合构建联合模型。上述模型在训练集中的AUC分别为0.818、0.886和0.896,在测试集中的AUC为0.785、0.866和0.870。结论基于DBT图像的影像组学特征术前可有效预测TNBC,为临床诊断TNBC提供新方法。Objective To explore the value of radiomics features based on digital breast tomosynthesis(DBT)images for preoperative prediction of triple⁃negative breast cancer(TNBC).Methods DBT images and clinical data of breast cancer patients were retrospectively analyzed,and a total of 198 patients were included according to the inclusion and exclusion criteria,which were classified into 146 cases of non⁃triple⁃negative breast cancer(NTNBC)and 52 cases of TNBC according to the pathological findings.The regions of interest(ROI)were delineated using 3D Slicer software,and radiomics features were extracted using Python,t⁃test and LASSO algorithm were used to select the features,and univariate analysis was used to select the clinical and imaging features.The models were constructed by support vector machine(SVM),and the area under the curve(AUC)and other indicators were used to evaluate the prediction performance of the models.Delong test was used to compare the AUC of each model.Results The age of menarche,mass with calcification,and BI⁃RADS grade(P<0.05)were selected to establish the clinical and imaging model,four important radiomics features were selected to establish the radiomics model,and features of the two groups were combined to construct a combined model.The AUCs of the above models in training set were:0.818,0.886 and 0.896,and in validation set were:0.785,0.866 and 0.870.Conclusion The radiomics features based on DBT images can effectively predict TNBC preoperatively,providing a new method for the clinical diagnosis of TNBC.

关 键 词：数字乳腺断层摄影 三阴性乳腺癌 影像组学 支持向量机 

分 类 号：R737.9[医药卫生—肿瘤]