Non-Linear Polynomial Filters for Edge Enhancement of Mammograms

Abstract

Non-linear polynomial filtering (NPF) framework has been explored previously as a robust approach for contrast improvement of mammographic images. However, NPF ‘Prototypes: α and β′ have been performance limited; as the contrast improvement has been accompanied with a severe background suppression in mammograms. This affected the visualization of other anatomical structures and diagnostic features in the vicinity of the ROI; these features equally contribute towards diagnostic decision making by radiologists. On the other hand, it is equally difficult to improve the edge strength and sharpness of the ROI without compromising the background content.