基于超声特征及反转评分的列线图在鉴别乳腺腺病与小乳腺癌中的临床价值初探  

Clinical Value of Nomogram Based on Ultrasound Features and Inverse Score in Differentiating Small Breast Cancer from Breast Adenosis

作　　者：刘晚玲 王佳佳 詹韵韵[1] 毕玉[1] 彭梅[1] Liu Wanling;Wang Jiajia;Zhan Yunyun;Bi Yu;Peng Mei(Department of Ultrasound Medicine,The Second Affiliated Hospital of Anhui Medical University,Hefei 230601,China)

机构地区：[1]安徽医科大学第二附属医院超声医学科,合肥市230601

出　　处：《中国超声医学杂志》2024年第7期737-741,共5页Chinese Journal of Ultrasound in Medicine

基　　金：安徽医科大学第二附属医院临床研究培育计划(No.2021LCZD06);2023年度安徽省高校自然科学研究项目(No.2023AH040373)。

摘　　要：目的 探讨基于超声特征及反转评分的列线图在鉴别诊断乳腺腺病与小乳腺癌中的临床价值。方法 回顾性分析经病理证实为乳腺腺病及小乳腺癌患者共计141例(143个肿块)的超声特征及反转评分,以7∶3比例随机分为训练集(n=100)和测试集(n=43)。在训练集中应用单因素分析、多因素逻辑回归分析,筛选出鉴别诊断乳腺腺病和小乳腺癌的独立预测变量并绘制列线图,使用受试者工作特征(ROC)曲线和C指数(C-index)评估模型的区分度,校准曲线评估模型校准度,并基于测试集数据验证模型诊断效能。结果 训练集结果显示,年龄、肿块血流信号、弹性评分、反转评分是鉴别诊断乳腺腺病与小乳腺癌的独立预测变量。基于上述变量绘制列线图和ROC曲线,曲线下面积为0.960,结果显示模型具有良好的区分度;校准曲线显示预测概率与实际概率一致性良好,提示模型校准度较高,内部验证及测试集显示列线图具有较高的诊断价值。结论 基于超声特征及反转评分绘制的列线图可以辅助临床鉴别诊断乳腺腺病与小乳腺癌,具有良好的临床应用价值。Objective To investigate the clinical value of nomogram based on ultrasound features and inverse score in the differential diagnosis of small breast cancer and breast adenosis.Methods A total of 141 patients with pathologically confirmed breast adenosis and small breast cancer(143 cases of mass) were retrospectively analyzed.The ultrasound features and inverse scores were randomly divided into the training set(n=100) and the validation set(n=43) at a ratio of 7∶3.In the training group,univariate and multivariate Logistic regression analysis was used to screen for the independent predictor variables for the differential diagnosis of breast adenosis and cancer,and a nomogram was built.The receiver operating characteristic(ROC) curve and C-index was used to evaluate the predictive value of the nomogram in the validation set.Results The results of the training set showed that age,blood flow signal,elasticity score and inverse score were independent predictors for the differential diagnosis of breast adenosis and small breast cancer.Based on the above variables,the area under the curve was 0.960,indicating that the model had good differentiation.The calibration curve showed that the predicted probability was in good agreement with the actual probability,indicating that the calibration degree of the model was high,and the nomogram shown by both internal and external verification had high diagnostic value.Conclusions The nomogram based on ultrasound features and inverse score can assist in the differential diagnosis of breast adenosis and small breast cancer,and has good clinical application value.

关 键 词：超声 乳腺腺病 乳腺癌 超声反转成像 列线图 

分 类 号：R445.1[医药卫生—影像医学与核医学] R737.9[医药卫生—诊断学]