Analysis of Co-Occurrence Texture Statistics as a Function of Gray-Level Quantization for Classifying Breast Ultrasound
Analysis of Co-Occurrence Texture Statistics as a Function of Gray-Level Quantization for Classifying Breast Ultrasound
复制标题
DOI：
10.1109/tmi.2012.2206398
复制
发表时间：
2012-10-01
影响因子：
10.6
通讯作者：
Infantosi, A. F. C.
中科院分区：
文献类型：
--
作者：
Gomez, W.;Pereira, W. C. A.;Infantosi, A. F. C.
在本文中，我们调查的行为22同现统计相结合的6个灰度量化水平，以分类乳腺病变超声（BUS）图像。本研究中使用的436个BUS图像数据库由217个癌和219个良性病变图像组成。病灶周围的最小外接矩形所界定的区域被用来计算灰度共生矩阵（GLCM）。接下来，关于六个量化级别（8、16、32、64、128和256）、四个取向（0度、45度、90度和135度）和十个距离（1、2、. 10像素）。此外，为了降低特征空间维数，相同距离的纹理描述符在所有方向上被平均，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（mRMR）准则对特征空间进行排序。Fisher线性判别分析（FLDA）被应用于评估纹理特征的区分能力，通过将第一个m-排名的特征迭代地添加到分类过程中，直到所有的特征都被考虑。使用ROC曲线下面积（AUC）作为品质因数来衡量分类器的性能。据观察，平均纹理描述符的相同的距离产生负面影响的分类性能，因为最好的AUC为0.81，实现了32个灰度级和109个功能。另一方面，关于单个纹理特征（即，没有平均过程），量化水平不影响辨别能力，因为对于六个量化水平获得AUC=0.87。此外，还减少了特征的数量（在17至24个特征之间）。纹理描述符，有助于显着区分乳腺病变的对比度和相关性计算的GLCM的方向为90度和距离超过5个像素。
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 degrees, 45 degrees, 90 degrees, and 135 degrees), 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 degrees and distance more than five pixels.