Computational unfoldment of mammograms

Abstract

The importance of mammograms in early breast cancer detection is an accepted fact. Mammograms (either an analog x-ray film or a digital softcopy) are computationally empowered to extract significant information. Several computational techniques/algorithms process mammograms to highlight and reveal otherwise unseen features. Thus mammographic images are computationally unfolded to obtain appropriate information that can be used for further analysis. Computational analysis of mammograms is an essential tool, which is used by numerous specialists for various purposes. In this paper we review such research work reported in the literature in recent years. Our focus is in particular on computational preprocessing of mammograms. Preprocessing involves enhancement of mammographic images as well as extraction of relevant features from images. We grouped various image enhancement research approaches systematically. We also categorized various research techniques based on the types of features that are extracted and used to obtain intended results. Although mammograms are used mostly for breast cancer detection, the research is not confined to this aspect only. Several other areas that deal with mammograms are also explored by researchers including image compression, Content based Image Retrieval (CBIR) etc. Variety in these research applications is also discussed and presented in this paper.