MR动态增强图像纹理分析判断乳腺结节良恶性的价值

发布时间：2018-04-14 22:21

本文选题：磁共振成像 + 纹理分析　；参考：《中国医学影像技术》2017年05期

【摘要】：目的探讨MR动态增强图像纹理分析鉴别诊断乳腺结节良恶性的价值。方法回顾性分析经手术病理证实的78例患者共80个乳腺结节的MR动态增强图像,每个结节获得63个纹理特征参数。绘制纹理参数鉴别诊断良恶性乳腺结节的ROC曲线,并与MR乳腺影像报告和数据系统(BI-RADS)的诊断效能比较。结果 78例患者的80个乳腺结节中,纹理参数中灰度游程长不均匀度判断乳腺结节良恶性的AUC值(0.836)最大且诊断准确率高,其诊断恶性乳腺结节的敏感度为82.93%(34/41)、特异度为94.87%(37/39)、准确率为88.75%(71/80)、阳性预测值为94.44%(34/36)、阴性预测值为84.09%(37/44)。MR BI-RADS分类诊断恶性乳腺结节的敏感度为95.12%(39/41)、特异度为87.18%(34/39)、准确率为91.25%(73/80)、阳性预测值为88.63%(39/44)、阴性预测值为94.44%(34/36)。MR BI-RADS分类和纹理分析判断恶性乳腺结节准确率差异无统计学意义(P=0.11)。与单独应用BI-RADS分类比较,两者联合应用可明显提高诊断恶性乳腺结节的特异度(P0.001)。结论MR纹理分析可作为传统诊断乳腺良恶性结节的补充。
[Abstract]:Objective to evaluate the value of texture analysis in dynamic enhanced Mr imaging in differential diagnosis of benign and malignant breast nodules.Methods dynamic contrast-enhanced Mr images of 80 breast nodules in 78 patients confirmed by surgery and pathology were retrospectively analyzed. 63 texture parameters were obtained for each node.The ROC curve of texture parameters for differential diagnosis of benign and malignant breast nodules was drawn and compared with the diagnostic efficacy of Mr mammography report and data system BI-RADS.Results among the 80 breast nodules in 78 patients, the AUC value of gray run length heterogeneity in texture parameters was 0.836) and the diagnostic accuracy was high.The negative predictive value was 94.44%(34/36).MR BI-RADS classification and texture analysis. There was no significant difference in the accuracy of malignant breast nodules.Compared with the classification of BI-RADS alone, the combination of the two methods can significantly improve the specificity of the diagnosis of malignant breast nodules (P 0.001).Conclusion Mr texture analysis can be used as a supplement for traditional diagnosis of benign and malignant breast nodules.
【作者单位】：新疆建设兵团第六师医院影像科;美国Moffitt癌症研究中心;国家癌症中心中国医学科学院北京协和医学院肿瘤医院PET/CT中心;
【分类号】：R445.2;R737.9

【相似文献】