The Investigation of the Effects of Different Filters on Mammogram Images

Mammogram is a widespread imaging technique to early detect breast cancer. It can detect micro scale calcium deposits (microcalcification) known as early signs of breast cancer., computer-aided diagnosis (CAD) systems are commonly used to detect of microcalcifications on mammograms. The first step of CAD system is cleaning noises on mammography images. In order to clean or decrease noise on images, several filters are used. The purpose of this study is denoising mammogram images that include micro calcification with different filters and comparing of filter results. For this, firstly 50 mammogram images are obtained from Digital Database for Screening Mammography (DDSM). Microcalcification located areas which stated in their data file on mammograms are cropped at 512x512 pixels. Each image matrices are filtered by median and moving average filter in spatial domain as well as high pass and low pass filter in frequency domain. The filtered images are compared by means of mean squared error (MSE) and peak signal-noise ratio (PSNR) after frequency domain filters contrast adjustment. At the end of the study, the optimal filter will be determined for cleaning mammograms without an effect on single or clustered microcalcification