乳腺影像报告数据系统超声图像特征预测乳腺癌风险的logistic模型及诊断效能研究  

A Logistic Regression Model Based on Breast Imaging Report And Data System Lexicon to Predict the Risk of Malignancy

作　　者：赵海娜[1] 彭玉兰[1] 骆洪浩[1] 何玉霜[1] 金亚[1] 杨盼[1] 

机构地区：[1]四川大学华西医院超声科,成都610041

出　　处：《华西医学》2015年第12期2249-2253,共5页West China Medical Journal

基　　金：四川省科技厅支撑项目(2012SZ0145);成都市科技局项目(12PPYB053SF-002)~~

摘　　要：目的利用乳腺影像报告数据系统(BI-RADS)超声图像特征,建立logistic回归模型,评估乳腺超声图像特征预测乳腺癌风险的诊断效能。方法回顾性分析2011年1月-9月经乳腺活体组织检查或手术的1 660例患者的乳腺超声图文资料,以BI-RADS标准对图像特征进行标准化处理,以病理结果为金标准,纳入单因素分析有诊断价值的超声图像特征建立logistic回归模型,探讨该模型预测乳腺癌风险的灵敏度、特异度和准确度。结果单因素分析发现30个超声图像特征中有18个对鉴别乳腺良恶性疾病有统计学意义(P<0.001),其中Cooper韧带受牵拉、强回声晕、皮肤增厚、腋窝淋巴结异常、结构扭曲、毛刺征比值比均在30以上,诊断乳腺恶性病变的特异度均>90%。基于这些图像特征建立的logistic回归模型诊断乳腺癌的灵敏度、特异度及准确度分别为84.5%、95.5%、91.4%,受试者工作特征曲线下面积为0.964,预报正确率为91.0%。结论基于BI-RADS超声图像特征的logistic回归模型预测乳腺癌风险有良好的诊断效能,预示规范化乳腺超声报告的大数据可建立乳腺癌临床决策系统,辅助超声医师提高诊断水平。Objective To establish logistic regression analysis model to evaluate the diagnostic ei cacy of breast imaging report and data system（BI-RADS） ultrasound signs in forecasting malignant risk of breast lesions. MethodsUltrasound graphic materials of 1 660 breast lesions diagnosed during January to September 2011 were retrospectively studied and standardized by BI-RADS. Pathology results were regarded as gold standard reference. Ultrasound signs with signii cant ei cacy at er single-factor logistic regression were evaluated in multi-factor logistic regression model to predict the malignant risk of breast lesions. Results Eighteen ultrasound signs of breast lesions on BI-RADS were included in the i nal regression model. Among them, Cooper ligaments stretch, echogenic halo, skin thickening, axillary lymph node abnormalities, structural distortions and speculation had high OR values of 30 or more and had higher specii city than 90%. The diagnosis values of regressions model were high, with a sensitivity of 84.5%, specificity 95.5% and accuracy 91.4%. h e area under ROC curve was 0.964 and prediction accuracy was 91.0%. Conclusion h e logistic regression model based on BI-RADS ultrasound signs of breast lesions has high diagnostic values in detecting breast cancer.

关 键 词：超声 乳腺影像报告数据系统 LOGISTIC回归模型 

分 类 号：R737.9[医药卫生—肿瘤] R445.1[医药卫生—临床医学]