Department of Radiology, Ewha Womans University Mokdong Hospital, Ewha Womans University School of Medicine, Seoul, Korea.
Department of Radiology and Research Institute of Radiology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Korea.
Ultrasonography. 2014 Apr;33(2):105-15. doi: 10.14366/usg.13023. Epub 2014 Feb 26.
The aim of this study was to evaluate the performance of a proposed computer-aided detection (CAD) system in automated breast ultrasonography (ABUS).
Eighty-nine two-dimensional images (20 cysts, 42 benign lesions, and 27 malignant lesions) were obtained from 47 patients who underwent ABUS (ACUSON S2000). After boundary detection and removal, we detected mass candidates by using the proposed adjusted Otsu's threshold; the threshold was adaptive to the variations of pixel intensities in an image. Then, the detected candidates were segmented. Features of the segmented objects were extracted and used for training/testing in the classification. In our study, a support vector machine classifier was adopted. Eighteen features were used to determine whether the candidates were true lesions or not. A five-fold cross validation was repeated 20 times for the performance evaluation. The sensitivity and the false positive rate per image were calculated, and the classification accuracy was evaluated for each feature.
In the classification step, the sensitivity of the proposed CAD system was 82.67% (SD, 0.02%). The false positive rate was 0.26 per image. In the detection/segmentation step, the sensitivities for benign and malignant mass detection were 90.47% (38/42) and 92.59% (25/27), respectively. In the five-fold cross-validation, the standard deviation of pixel intensities for the mass candidates was the most frequently selected feature, followed by the vertical position of the centroids. In the univariate analysis, each feature had 50% or higher accuracy.
The proposed CAD system can be used for lesion detection in ABUS and may be useful in improving the screening efficiency.
本研究旨在评估一种拟议的计算机辅助检测（CAD）系统在自动乳腺超声（ABUS）中的性能。
从 47 名接受 ABUS（ACUSON S2000）检查的患者中获得 89 个二维图像（20 个囊肿、42 个良性病变和 27 个恶性病变）。边界检测和去除后，我们使用所提出的调整后的 Otsu 阈值来检测肿块候选物；该阈值适应图像中像素强度的变化。然后，检测候选物被分割。分割对象的特征被提取并用于分类的训练/测试。在我们的研究中，采用了支持向量机分类器。采用 18 个特征来确定候选物是否为真正的病变。进行了 20 次五次交叉验证以进行性能评估。计算了每个图像的灵敏度和假阳性率，并评估了每个特征的分类准确性。
在分类步骤中，所提出的 CAD 系统的灵敏度为 82.67%（SD，0.02%）。假阳性率为每幅图像 0.26。在检测/分割步骤中，良性和恶性肿块检测的灵敏度分别为 90.47%（38/42）和 92.59%（25/27）。在五次交叉验证中，肿块候选物的强度像素的标准差是最常被选择的特征，其次是质心的垂直位置。在单变量分析中，每个特征的准确性都在 50%或更高。
所提出的 CAD 系统可用于 ABUS 中的病变检测，可能有助于提高筛查效率。
