弹性成像结合卡方自动交互检测法在鉴别乳腺肿块良恶性中的应用

目的利用卡方自动交互检测法开发一种简单的算法来鉴别乳腺肿块的良恶性。方法经过病理证实的201例乳腺肿块患者纳入此项研究,每例患者都有一个乳腺肿块经常规超声检查、声触诊组织成像(VTI)及声触诊组织量化(VTQ)技术成像,并测量出VTI面积比(肿块VTI面积或肿块二维面积)及肿块VTQ或腺体VTQ。利用受试者操作特性曲线评价各项超声弹性成像参数的诊断性能,再使用卡方自动交互检测法进行分类分析。结果分类算法包括肿块VTQ及VTI面积比,其深度为两个分支(肿块VTQ>3.958或≤3.958,如果肿块VTQ≤3.958接着考虑VTI面积比≤1.304或1.304~1.493或>1.493)。分类算法的AUC为0.901、灵敏度为98.2%、特异度为68.1%,应用该算法,有30.8%的病例可以避免活检。结论联合应用肿块VTQ及VTI面积比的分类算法具有较高的诊断性能,准确度达97%,减少30%以上不必要的穿刺活检。

Application of Ultrasound Elastography Combined with Chi-squared Automatic Interaction Detector in Differentiating Benign From Malignant Breast Masses

Objective The goal of our study was to develop a simple algorithm by using chi-square automatic interactive detection to identify the benign and malignant breast masses.Methods Pathologicgically confirmed 201 cases of breast masses were included in this study.Each patient had a breast mass that examined with conventional ultrasound examination,VTI and VTQ,and VTI area ratio(mass VTI area/mass two-dimensional area)and mass VTQ/gland VTQ were measured.The diagnostic performance of various ultrasound elastography parameters was evaluated using receiver operating characteristic curve,and the chi-square automatic interactive detection method was used for classification and analysis.Results In all ultrasound elastography parameters,the classification algorithm includes mass VTQ and VTI area ratio,and the depth was divided into two branches(mass VTQ≤or>3.958;if mass VTQ ≤3.16 then VTI area ratio≤1.304,1.304-1.493 or>1.493).The classification algorithm leads to an AUC of 0.901,a sensitivity of 98.2 %,and a specificity of 68.1%.By applying the proposed algorithm,a biopsy could have been avoided in 30.8 % of the cases.Conclusions The classification algorithm combined with mass VTQ and VTI area ratio has high diagnostic performance,with nearly 97% accuracy and over 30% reduction of unnecessary puncture biopsy.