Meel-van den Abeelen A S S, Weijers G, van Zelst J C M, Thijssen J M, Mann R M, de Korte C L
Department of Biomechanical Engineering, MIRA-Institute, University of Twente, P.O. Box 217, 7500 AE Enschede, The Netherlands; Medical UltraSound Imaging Center (MUSIC), department of Radiology and Nuclear Medicine, Radboud University Medical Center, P.O. Box 9101, 6500 HB Nijmegen, The Netherlands.
Medical UltraSound Imaging Center (MUSIC), department of Radiology and Nuclear Medicine, Radboud University Medical Center, P.O. Box 9101, 6500 HB Nijmegen, The Netherlands.
Eur J Radiol. 2017 Mar;88:141-147. doi: 10.1016/j.ejrad.2017.01.006. Epub 2017 Jan 8.
In (3D) ultrasound, accurate discrimination of small solid masses is difficult, resulting in a high frequency of biopsies for benign lesions. In this study, we investigate whether 3D quantitative breast ultrasound (3DQBUS) analysis can be used for improving non-invasive discrimination between benign and malignant lesions.
3D US studies of 112 biopsied solid breast lesions (size <1cm), were included (34 fibroadenomas and 78 invasive ductal carcinomas). The lesions were manually delineated and, based on sonographic criteria used by radiologists, 3 regions of interest were defined in 3D for analysis: ROI (ellipsoid covering the inside of the lesion), PER (peritumoural surrounding: 0.5mm around the lesion), and POS (posterior-tumoural acoustic phenomena: region below the lesion with the same size as delineated for the lesion). After automatic gain correction (AGC), the mean and standard deviation of the echo level within the regions were calculated. For the ROI and POS also the residual attenuation coefficient was estimated in decibel per cm [dB/cm]. The resulting eight features were used for classification of the lesions by a logistic regression analysis. The classification accuracy was evaluated by leave-one-out cross-validation. Receiver operating characteristic (ROC) curves were constructed to assess the performance of the classification. All lesions were delineated by two readers and results were compared to assess the effect of the manual delineation.
The area under the ROC curve was 0.86 for both readers. At 100% sensitivity, a specificity of 26% and 50% was achieved for reader 1 and 2, respectively. Inter-reader variability in lesion delineation was marginal and did not affect the accuracy of the technique. The area under the ROC curve of 0.86 was reached for the second reader when the results of the first reader were used as training set yielding a sensitivity of 100% and a specificity of 40%. Consequently, 3DQBUS would have achieved a 40% reduction in biopsies for benign lesions for reader 2, without a decrease in sensitivity.
This study shows that 3DQBUS is a promising technique to classify suspicious breast lesions as benign, potentially preventing unnecessary biopsies.
在三维（3D）超声检查中，准确鉴别小的实性肿块存在困难，导致良性病变的活检频率较高。在本研究中，我们探究三维定量乳腺超声（3DQBUS）分析是否可用于提高对良性和恶性病变的无创鉴别能力。
纳入了112个经活检的乳腺实性病变（大小<1cm）的三维超声研究（34个纤维腺瘤和78个浸润性导管癌）。手动勾勒病变轮廓，并根据放射科医生使用的超声标准，在三维空间中定义3个感兴趣区域进行分析：ROI（覆盖病变内部的椭球体）、PER（肿瘤周围：病变周围0.5mm）和POS（肿瘤后方声学现象：病变下方与病变勾勒大小相同的区域）。在自动增益校正（AGC）后，计算各区域内回声水平的平均值和标准差。对于ROI和POS，还估计了以分贝每厘米[dB/cm]为单位的残余衰减系数。所得的八个特征用于通过逻辑回归分析对病变进行分类。通过留一法交叉验证评估分类准确性。构建受试者操作特征（ROC）曲线以评估分类性能。所有病变均由两名阅片者勾勒轮廓，并比较结果以评估手动勾勒的影响。
两位阅片者的ROC曲线下面积均为0.86。在灵敏度为100%时，阅片者1和阅片者2的特异度分别为26%和50%。阅片者之间在病变勾勒方面的差异很小，且不影响该技术的准确性。当将第一位阅片者的结果用作训练集时，第二位阅片者的ROC曲线下面积达到0.86，灵敏度为100%，特异度为40%。因此，对于阅片者2而言，3DQBUS可使良性病变的活检减少40%，且不降低灵敏度。
本研究表明，3DQBUS是一种有前景的技术，可将可疑乳腺病变分类为良性，有可能避免不必要的活检。
