CAD在乳腺纤维腺瘤钼靶X线诊断中的应用

The Value of CAD in the Mammography Diagnosis for Breast Fibroadenoma

目的:探讨计算机辅助检测(CAD)在乳腺纤维腺瘤钼靶X线诊断中的应用价值。方法:收集本院109例乳腺纤维腺瘤患者的钼靶图像,使用CAD系统标识感兴趣区域(ROIs)并观察系统勾画的病灶位置及形状,探讨CAD在乳腺纤维腺瘤诊断中的应用价值。结果:在109例乳腺纤维腺瘤患者钼靶图像中,CAD系统对脂肪型乳腺的识别率最高,达到100%,对致密型、多量腺体型和少量腺体型乳腺的识别率分别为5.88%、5.41%和4.55%。结论:CAD能够识别高于其周围腺体组织密度的乳腺纤维腺瘤,本结论对于数字图像处理的优化研究有一定参考价值。

Objective:To investigate the value of computer-aided detection(CAD)in the diagnosis of mammography for breast fibroadenoma.Methods:We collected 109 breast fibroadenoma patients’mammogram images,identifiedthe regions of interest(ROIs)by using CAD software,and observed the breast lumps’location and shape.Results:Among the mammograms of 109 breast fibroadenoma patients,the CAD software has the 100%recognition rate for fatty breasts,and 5.88%,5.41%and 4.55%for dense breasts,multiple glandular breastsand small amounts of glandular breasts,respectively.Conclusions:CAD could identify breast fibroadenoma with higher density than its surrounding glandular tissue,and the conclusion providescertain reference values for the optimization of image processing software.