A multi-resolution approach to denoising and enhancement of pre-cancerous features in mammograms
C. Gowri Shankar, T. Balakumaran, A. Shanmugam · International Journal of Biomedical Engineering and Technology · 2011
Microcalcification is the earliest sign of breast carcinomas and their detection is the key issues for breast cancer control. The existence of noise degrades the subjective quality of image and makes the decision incorrect. A wide variety of filtering algorithms have been developed for preprocessing, but some causes unpleasant visual artifacts. Here multi-scale products are used at successive scales of Wavelet decomposition, obtained by multiplying the coefficients of successive wavelet scale. This would strengthen the significant features while weakening the noise. Testing shows that the proposed scheme better suppresses noise and enhances the objective areas than other methods.