Technology Information Laboratory, Center for Research and Advanced Studies of the National Polytechnic Institute, Ciudad Victoria, 87130 Tamaulipas, Mexico.
IEEE Trans Med Imaging. 2012 Oct;31(10):1889-99. doi: 10.1109/TMI.2012.2206398. Epub 2012 Jun 28.
In this paper, we investigated the behavior of 22 co-occurrence statistics combined to six gray-scale quantization levels to classify breast lesions on ultrasound (BUS) images. The database of 436 BUS images used in this investigation was formed by 217 carcinoma and 219 benign lesions images. The region delimited by a minimum bounding rectangle around the lesion was employed to calculate the gray-level co-occurrence matrix (GLCM). Next, 22 co-occurrence statistics were computed regarding six quantization levels (8, 16, 32, 64, 128, and 256), four orientations (0° , 45° , 90° , and 135°), and ten distances (1, 2,...,10 pixels). Also, to reduce feature space dimensionality, texture descriptors of the same distance were averaged over all orientations, which is a common practice in the literature. Thereafter, the feature space was ranked using mutual information technique with minimal-redundancy-maximal-relevance (mRMR) criterion. Fisher linear discriminant analysis (FLDA) was applied to assess the discrimination power of texture features, by adding the first m-ranked features to the classification procedure iteratively until all of them were considered. The area under ROC curve (AUC) was used as figure of merit to measure the performance of the classifier. It was observed that averaging texture descriptors of a same distance impacts negatively the classification performance, since the best AUC of 0.81 was achieved with 32 gray levels and 109 features. On the other hand, regarding the single texture features (i.e., without averaging procedure), the quantization level does not impact the discrimination power, since AUC = 0.87 was obtained for the six quantization levels. Moreover, the number of features was reduced (between 17 and 24 features). The texture descriptors that contributed notably to distinguish breast lesions were contrast and correlation computed from GLCMs with orientation of 90° and distance more than five pixels.
本文研究了 22 种共生统计量与 6 种灰度量化级相结合的行为，以对超声 (BUS) 图像中的乳腺病变进行分类。本研究使用的 436 张 BUS 图像数据库由 217 个癌和 219 个良性病变图像组成。使用病变最小外接矩形所限定的区域来计算灰度共生矩阵 (GLCM)。然后，针对六个量化级 (8、16、32、64、128 和 256)、四个方向 (0°、45°、90°和 135°) 和十个距离 (1、2、…、10 像素) 计算了 22 种共生统计量。此外，为了降低特征空间的维度，还将同一距离的纹理描述符在所有方向上进行平均，这是文献中的常见做法。然后，使用互信息技术和最小冗余最大相关性 (mRMR) 准则对特征空间进行排序。Fisher 线性判别分析 (FLDA) 用于通过将前 m 个特征添加到分类过程中迭代地评估纹理特征的判别能力，直到考虑到所有特征。ROC 曲线下面积 (AUC) 被用作衡量分类器性能的度量标准。观察到，对同一距离的纹理描述符进行平均会对分类性能产生负面影响，因为在使用 32 个灰度级和 109 个特征时，最佳 AUC 为 0.81。另一方面，对于单个纹理特征（即，不进行平均处理），量化级不会影响判别能力，因为在六个量化级下，AUC 为 0.87。此外，特征数量减少了（17 到 24 个特征之间）。对区分乳腺病变有重要贡献的纹理描述符是对比度和相关性，它们是从 GLCM 计算得出的，方向为 90°，距离大于 5 个像素。
