Characterization and classification of tumor lesions using computerized fractal-based texture analysis and support vector machines in digital mammograms

Objective: This paper presents a detailed study of fractal-based methods for texture characterization of mammographic mass lesions and architectural distortion. The purpose of this study is to explore the use of fractal and lacunarity analysis for the characterization and classification of both tumor lesions and normal breast parenchyma in mammography. Materials and methods: We conducted comparative evaluations of five popular fractal dimension estimation methods for the characterization of the texture of mass lesions and architectural distortion. We applied the concept of lacunarity to the description of the spatial distribution of the pixel intensities in mammographic images. These methods were tested with a set of 57 breast masses and 60 normal breast parenchyma (dataset1), and with another set of 19 architectural distortions and 41 normal breast parenchyma (dataset2). Support vector machines (SVM) were used as a pattern classification method for tumor classification. Results: Experimental results showed that the fractal dimension of region of interest (ROIs) depicting mass lesions and architectural distortion was statistically significantly lower than that of normal breast parenchyma for all five methods. Receiver operating characteristic (ROC) analysis showed that fractional Brownian motion (FBM) method generated the highest area under ROC curve (A z = 0.839 for dataset1, 0.828 for dataset2, respectively) among five methods for both datasets. Lacunarity analysis showed that the ROIs depicting mass lesions and architectural distortion had higher lacunarities than those of ROIs depicting normal breast parenchyma. The combination of FBM fractal dimension and lacunarity yielded the highest A z value (0.903 and 0.875, respectively) than those based on single feature alone for both given datasets. The application of the SVM improved the performance of the fractal-based features in differentiating tumor lesions from normal breast parenchyma by generating higher A z value. Conclusion: FBM texture model is the most appropriate model for characterizing mammographic images due to self-affinity assumption of the method being a better approximation. Lacunarity is an effective counterpart measure of the fractal dimension in texture feature extraction in mammographic images. The classification results obtained in this work suggest that the SVM is an effective method with great potential for classification in mammographic image analysis.

Intra-tumor heterogeneity: lessons from microbial evolution and clinical implications

Multiple subclonal populations of tumor cells can coexist within the same tumor. This intra-tumor heterogeneity will have clinical implications and it is therefore important to identify factors that drive or suppress such heterogeneous tumor progression. Evolutionary biology can provide important insights into this process. In particular, experimental evolution studies of microbial populations, which exist as clonal populations that can diversify into multiple subclones, have revealed important evolutionary processes driving heterogeneity within a population. There are transferrable lessons that can be learnt from these studies that will help us to understand the process of intra-tumor heterogeneity in the clinical setting. In this review, we summarize drivers of microbial diversity that have been identified, such as mutation rate and environmental influences, and discuss how knowledge gained from microbial experimental evolution studies may guide us to identify and understand important selective factors that promote intra-tumor heterogeneity. Furthermore, we discuss how these factors could be used to direct and optimize research efforts to improve patient care, focusing on therapeutic resistance. Finally, we emphasize the need for longitudinal studies to address the impact of these potential tumor heterogeneity-promoting factors on drug resistance, metastatic potential and clinical outcome.