3D Lacunarity in Multifractal Analysis of Breast Tumor Lesions in Dynamic Contrast-Enhanced Magnetic Resonance Imaging

Abstract

Dynamic contrast-enhanced magnetic resonance (DCE-MR) of the breast is especially robust for the diagnosis of cancer in high-risk women due to its high sensitivity. Its specificity may be, however, compromised since several benign masses take up contrast agent as malignant lesions do. In this paper, 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 properties are extracted from the estimation of the multifractal scaling exponent for each clinical case, using lacunarity as the multifractal measure. These properties 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 classification method evaluated by receiver operating characteristics with an area under the curve of 0.96. In addition, this paper 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 have the potential to complement the interpretation of the radiologists and supply a computer-aided diagnosis system.

Breast cancer subtype intertumor heterogeneity: MRI‐based features predict results of a genomic assay

“…Computer extracted histogram-based image features have been shown to correlate with phenotypic heterogeneity. 15,16 We have also demonstrated that there are characteristics that are not readily appreciated visually but can be 22 have used fractal-based methods to extract data to characterize breast cancer spatial complexity. Finally, multiparametric MRI, which is helpful in distinguishing benign and malignant breast pathology, may also prove helpful in generating phenotypic biomarkers.…”

“…For example, Ahmed et al 30 evaluated the ability of MRI textural analysis in predicting breast cancer response to chemotherapy and concluded that significant texture parameters and groupings were observed and differed between responders and nonresponders. Soares et al 22 have used fractal-based methods to extract data to characterize breast cancer spatial complexity. Finally, multiparametric MRI, which is helpful in distinguishing benign and malignant breast pathology, may also prove helpful in generating phenotypic biomarkers.…”

“…Other works have studied the utility of a variety of texture features including edge-based features, fractals, and variations of GLCM features. 21,22 In this work, we restricted the analysis to the three types of features, as these capture both the internal and external (shape)-based intensity characteristics of the tumors. The lack of positive predictive power for morphological/edge-based features may be due to our limited quantification of the tumor surface, given our use of a single central tumor slice.…”

“…Previous applications of texture analysis for breast cancer have predominantly been for differentiating between benign and malignant lesions as well as differentiating between ductal and lobular breast cancers. [17][18][19][20] Sophisticated methods using gray-scale correlation matrix (GLCM) textures or variations of the same textures computed from Gabor edge images and temporal kinetics, 21 as well as fractal-based textures, 22 have been employed for classifying malignant from benign breast tumors. The purpose of this study was to investigate the association between ODxRS and image analysis-based features extracted from MRI scans.…”

Fibrous Dysplasia Characterization Using Lacunarity Analysis

“…Lacunarity could also be used to quantify the severity of disease or to differentiate benign from malignant tumors. Literature presents various examples of the use of lacunarity in other scenarios, such as to assess osteoporosis [12], microvascular morphology [26], to analyze the behavior of prostate cancer [27] and breast tumor lesions [28], and to measure cell cancer behavior [29].…”