Performance Evaluation of Denoising Techniques Applied to Mammograms of Dense Breasts

Abstract

Research indicates out that early diagnosis of the tumor may increase the chance of disease treatment and currently, the most effective method for early detection of illness is mammography. For this reason, using techniques that result in better quality images, that is, with as little noise as possible can aid in the visualization and detection of lesions and improve the accuracy of the diagnosis. For this work were used three filters being them: Wiener, Lee and Frost and to measure its efficiency were used the following parameters: Peak Signal to Noise-Ratio (PSNR), Signal to Noise-Ratio (SNR) and Structural SIMilarity (SSIM). It was verified that the Wiener filter presented better performance when compared to the others.