Comparative analysis of different enhancement method on digital mammograms

Abstract

Mammogram breast cancer images have the ability to assist physician in detection disease caused by cells abnormal growth. Developing algorithms and software to analyse these images may also assist physicians in their daily work. Microcalcifications are tiny calcium deposits in breast tissues. They appear as small bright spots on mammograms. Since microcalcifications are small and subtle abnormalities, they may be overlooked by an examining radiologist. Image Enhancement and Filtering is always the root process in many medical image processing applications. It is aimed at reducing noise in images. In this paper we have made comparison between several novel and hybrid enhancement techniques. The comparison is based on the basis of observations (from the clinical point of view) and performance evaluation parameters (statistical parameter) such as PSNR, and CNR. These can be used for identifying breast nodule malignancy to provide better chance of a proper treatment. These methods are tested on digital mammograms present in mini-MIAS database.