Gradient and texture analysis for the classification of mammographic masses
Gradient and texture analysis for the classification of mammographic masses
复制标题
DOI：
10.1109/42.887618
复制
发表时间：
2000-10-01
影响因子：
10.6
通讯作者：
Desautels, JEL
中科院分区：
文献类型：
--
作者：
Mudigonda, NR;Rangayyan, RM;Desautels, JEL
本研究尝试以电脑辅助分类的良恶性肿块的乳房X光片，计算基于梯度和纹理的功能。基于灰度共生矩阵（GCM）计算的特征被用来评估质量区域所拥有的纹理信息与质量边缘中存在的纹理信息相比的有效性。提出了一种多边形边界建模的方法，用于提取跨质量边缘的像素带。两个基于梯度的特征被开发来估计从其边缘提取的像素带中的质量边界的锐度，总共54幅图像分析了包含来自乳腺摄影图像分析协会（MIAS）数据库的39幅图像和来自本地数据库的15幅图像的28幅良性和26幅恶性图像，最佳良性与恶性分类为82.1%，受试者工作特征（ROC）曲线下的面积（A（z））为0.85，通过使用从质量边缘计算的基于GCM的纹理特征，利用来自MIAS数据库的图像获得。所使用的分类方法是基于从马氏距离计算的后验概率。观察到使用折刀分类的相应准确度为74.4%，其中A（z）= 0.67，基于一致性的特征在MIAS数据库上达到A（z）= 0.6，在组合数据库上达到A（z）= 0.76。观察到MIAS和合并数据库使用折刀分类获得的相应值分别为0.52和0.73。
Computer-aided classification of benign and malignant masses on mammograms is attempted in this study by computing gradient-based and texture-based features. Features computed based on gray-level co-occurrence matrices (GCMs) are used to evaluate the effectiveness of textural information possessed by mass regions in comparison with the textural information present in mass margins. A method involving polygonal modeling of boundaries is proposed for the extraction of a ribbon of pixels across mass margins. Two gradient-based features are developed to estimate the sharpness of mass boundaries in the ribbons of pixels extracted from their margins, A total of 54 images (28 benign and 26 malignant) containing 39 images from the Mammographic Image Analysis Society (MIAS) database and 15 images from a local database are analyzed, The best benign versus malignant classification of 82.1%, with an area (A(z)) of 0.85 under the receiver operating characteristics (ROC) curve, was obtained with the images from the MIAS database by using GCM-based texture features computed from mass margins. The classification method used is based on posterior probabilities computed from Mahalanobis distances. The corresponding accuracy using jack-knife classification was observed to be 74.4%, with A(z) = 0.67, Gradient-based features achieved A(z) = 0.6 on the MIAS database and A(z) = 0.76 on the combined database. The corresponding values obtained using jack-knife classification were observed to be 0.52 and 0.73 for the MIAS and combined databases, respectively.