含瘤周组织的超声影像组学在鉴别乳腺结节良恶性中的价值  

Clinical value of ultrasound radiomics based on peritumour-containing tissues in identifying benign and malignant breast nodules

作　　者：卢晓颂 杨瑞敏[1] 王义成[1] 周海丰[2] 罗兵[1] 李晓宇 李娜娜 LU Xiaosong;YANG Ruimin;WANG Yicheng;ZHOU Haifeng;LUO Bing;LI Xiaoyu;LI Nana(Department of Ultrasound,The Frist Affiliated Hospital of Hebei North University,Zhangjiakou 075000,Hebei,China;Department of Breast Surgray,The Frist Affiliated Hospital of Hebei North University,Zhangjiakou 075000,Hebei,China;Graduate School,Hebei North University,Zhangjiakou 075000,Hebei,China)

机构地区：[1]河北北方学院附属第一医院超声医学科,河北张家口075000 [2]河北北方学院附属第一医院乳腺外科,河北张家口075000 [3]河北北方学院研究生学院,河北张家口075000

出　　处：《山东大学学报(医学版)》2025年第1期90-98,共9页Journal of Shandong University:Health Sciences

基　　金：河北省医学科学研究计划项目(20220606)。

摘　　要：目的基于超声瘤内及含瘤周2 mm、4 mm区域构建影像组学模型,预测其在鉴别乳腺结节良恶性中的临床诊断价值。方法回顾性收集220例超声诊断为乳腺结节且在河北北方学院附属第一医院进行手术的女性患者的超声图像,按照7∶3的比例将乳腺结节图像随机分为训练集(n=154)和测试集(n=66),在乳腺结节最大切面图像勾画感兴趣区(region of interest,ROI),即瘤内组,并且分别自动适形外扩2 mm、4 mm,得到含瘤周2 mm组、含瘤周4 mm组;通过LASSO回归筛选出最优影像组学特征,建立逻辑回归模型,用AUC、敏感度、特异度及约登指数比较影像组学模型在训练集和测试集的诊断价值,采用Delong检验比较各影像组学模型之间的统计学差异,采用校准曲线和决策曲线评估影像组学模型的预测效能。结果含瘤周4 mm组的影像组学模型较另外两种模型效能更佳。在训练集中,瘤内组、含瘤周2 mm组及含瘤周4 mm组的AUC分别为0.886、0.902、0.945;在测试集中,瘤内组、含瘤周2 mm组及含瘤周4 mm组的AUC分别为0.793、0.757、0.901。在训练集中,瘤内组、含瘤周2 mm组模型分别与含瘤周4 mm组模型之间AUC对比,Delong检验P均<0.05。在训练集中,含瘤周4 mm组的敏感度、特异度及约登指数分别为0.927、0.833、0.760,在测试集中含瘤周4 mm组的敏感度、特异度及约登指数分别为0.879、0.818、0.697。结论与瘤内组模型和含瘤周2 mm组模型相比,基于超声含瘤周4 mm组的影像组学模型鉴别乳腺结节良恶性有更好的预测价值。Objective To construct the radiomics model of ultrasound based on intratumoral and peritumoral 2 mm and 4 mm regions and to predict the clinical diagnostic value of these models in identifying benign and malignant breast nodules.Methods Retrospective collection of the ultrasound images of 220 female patients diagnosed as breast nodules by ultrasound were performed.The patients underwent surgery at the Frist Affiliated Hospital of Hebei North University.The breast nodule ultrasound images were randomly divided into a training set(n=154)and a test set(n=66)in a ratio of 7∶3.The region of interest(ROI)was outlined as the intratumoral group on the maximal section image of the breast nodule and automatically conformed to the outward extension of 2 mm and 4 mm,respectively,to obtain the peritumoral 2 mm group and peritumoral 4 mm group.The optimal imaging histological features of the intratumoral group,peritumoral 2 mm group and peritumoral 4 mm group were screened by LASSO regression to construct a Logistic regression models.The diagnostic efficacy of the models in the training set and test set were evaluated using AUC,sensitivity,specificity and Jordon index,and the statistical difference among the models were verified using Delong test.The predictive efficacy of radiomics models were assessed using calibration and decision curves.Results Among the three groups,the radiomics model of the peritumoral 4mm group had the best efficacy.The values of AUC in the intratumoral group,peritumoral 2 mm group and peritumoral 4 mm group in the training set were 0.886,0.902,and 0.945,while those in the testing set were 0.793,0.757,0.901,respectively.In the training set,the values of AUC in the intratumoral group and the peritumoral 2 mm group were statistical different with that in the peritumoral 4 mm group(both P<0.05).The sensitivity,specificity and Yoden index of the peritumoral 4 mm group in the training set and test set were 0.927,0.833,0.760,and 0.879,0.818,0.697,respectively.Conclusion The ultrasound-based radiomics model

关 键 词：超声 影像组学 乳腺结节 瘤内区域 瘤周区域 

分 类 号：R445.1[医药卫生—影像医学与核医学]