Computer-aided classification of breast masses using speckle features of automated breast ultrasound images

To develop an ultrasound computer-aided diagnosis (CAD) system using speckle features of automated breast ultrasound (ABUS) images.

The ABUS images of 147 pathologically proven breast masses (76 benign and 71 malignant cases) were used. For each mass, a volume of interest (VOI) was cropped to define the tumor area, and the average number of speckle pixels within a VOI was calculated. In addition, first-order and second-order statistical analyses of the speckle pixels were used to quantify the information of gray-level distributions and the spatial relations among the pixels. Receiver operating characteristic curve analysis was used to evaluate the performance.

The proposed CAD system based on speckle patterns achieved an accuracy of 84.4% (124∕147), a sensitivity of 83.1% (59∕71), a specificity of 85.5% (65∕76), and an Az of 0.91. The performance indices of the speckle features were comparable to the performance indices of the morphological features, which include shape and ellipse-fitting features (p-value > 0.05). Furthermore, combining speckle and morphological features yielded an Az that was significantly better than the Az of the morphological features alone (0.96 vs 0.91, p-value = 0.0154).

The results suggest that the proposed speckle features, while combined with morphological features, are promising for the classification of breast masses detected using ABUS.