A tool supported approach for brightness preserving contrast enhancement and mass segmentation of mammogram images using histogram modified grey relational analysis

Mammography is a tool that uses X-rays to create mammograms. This tool is mainly used to find early signs of breast cancer. Usually, mammogram image contains region with low contrast and complicated structured background. This may cause difficulties in detection of infected cells in their early stage. Using contrast enhancement of mammogram image we can increase the detection rate of early breast cancer. In this paper we propose a tool supported method named histogram modified grey relational analysis, based on HE with local contrast enhancement for mammogram images. This method enhances local as well as global contrast of given mammogram image and segments breast region in order to obtain better visual interpretation, analysis, and classification of mammogram masses to assist radiologists in making more accurate decisions. The main contribution of this work is to show that better breast-region segmentation results can be achieved from simple breast-region segmentation method if the input image has sufficient contrast with good interpretation of local details. We tested proposed method for MIAS mammogram images. To evaluate effectiveness of proposed method we choose three widely used metrics absolute mean brightness error, structural similarity index measure and peak signal to noise ratio for all 322 images of MIAS mammogram images database.