Modified Algorithm for Denoising of Mammographic Images

Mammographic images are used for detection of breast cancer in women. In this paper denoising algorithms for mammographic images in wavelet domain are considered. A modified approach for denoising of mammographic images using Diversity Enhanced Wavelet Transform has been proposed. Diversity of the Wavelet Transform is enhanced by taking different mother wavelets and different number of levels to select for the optimized set of mother wavelet and number of iterations which results in maximum PSNR value. Proposed method is applied on large data set of digital mammographic images with four different types of thresholding: Bayesian shrink,Visu shrink, Neighbourhood shrink and Modified Neighbourhood shrink. The results are compared with the Discrete Wavelet Transform method using Peak Signal to Noise Ratio (PSNR) in dB and Mean Square Error (MSE). Results clearly indicate the superiority of the proposed method in all the four cases over exiting wavelet based method.