Mammogram diagnostics via 2-D complex wavelet-based self-similarity measures

Breast cancer is the second leading cause of death in women in the United States. Mammography is currently the most effective method for detecting breast cancer early; however, radiological interpretation of mammogram images remains a challenging task. On the other hand, many medical images demonstrate a certain degree of self-similarity over a range of scales which can guide us in their description and classification. In this work, we generalize the scale-mixing wavelet transform to the complex wavelet domain. In this domain, we estimate Hurst parameter and phase and use them as discriminatory descriptors to classify mammographic images to benign and malignant. The proposed methodology is tested on a set of images from the University of South Florida Digital Database for Screening Mammography (DDSM).