A comparative study on super-resolution methods for enhanced micro, macro and calcification on digital mammograms: Multi-scale iterative resolution with wavelet and cosine transform

Breast cancer is worldwide the second cause of death by cancer in women. Digital mammogram analysis is one of the best diagnostic tools for detecting breast cancer in early stages, leading to improve the probability of survival and reducing treatment costs. A major problem in digital mammogram analysis is due the low resolution and poor contrast of microcalcifications, in the region of interest. In this paper, a iterative method for super-resolution in mammograms, is presented. The proposed approach is tested using wavelet and cosine transform. Comparisons to the most prominent competing state of the art methods using four different metrics are performed, demonstrating the validity and effectiveness of our proposed multi-scale iterative resolution method.