IEEE Transactions on Image Processing
IEEE Transactions on Image Processing
复制标题
DOI：
10.1109/tip.83
复制
发表时间：
2004
期刊：
影响因子：
--
通讯作者：
中科院分区：
文献类型：
--
作者：
1摘要 - 乳房的乳房增强磁共振尤其可用于高风险女性的癌症，因为其高灵敏度可能会损害其特异性。在本文中，我们提出了一种新型的3D多重分析方法，以表征乳腺肿瘤在多个尺度上的空间复杂性（纹理的空间排列）。从对每个临床情况的多重尺度缩放指数的估计中提取自相似的所有权，这些术语是多重测量的，这些所有权包括多种谱系的多种描述符，以反映出相对较高的正常病态的内部空间结构结果。结果表明，组合的多重特征可以有效区分良性和恶性发现支持向量机（SVM）分类方法通过接收器操作特征（ROC），曲线下的面积为0.96。在多个尺度上占上风。
1 Abstract—Dynamic contrast-enhanced magnetic resonance of the breast is especially robust for the diagnosis of cancer in high-risk women due to its high sensitivity. However, its specificity may be compromised since several benign masses take up contrast agent as malignant lesions do. In this article, we propose a novel method of 3D multifractal analysis to characterize the spatial complexity (spatial arrangement of texture) of breast tumors at multiple scales. Self-similar proprieties are extracted from the estimation of the multifractal scaling exponent for each clinical case, using lacunarity as the multifractal measure. These proprieties include several descriptors of the multifractal spectra reflecting the morphology and internal spatial structure of the enhanced lesions relatively to normal tissue. The results suggest that the combined multifractal characteristics can be effective to distinguish benign and malignant findings, judged by the performance of the support vector machine (SVM) classification method evaluated by receiver operating characteristics (ROC) with an area under the curve of 0.96. Moreover, the study confirms the presence of multifractality in DCE-MR volumes of the breast, whereby multiple degrees of self-similarity prevail at multiple scales. The proposed feature extraction and classification method has the potential to complement the interpretation of the radiologists and supply a computer-aided diagnosis (CADx) system.