A Contour Based Approach for Bilateral Mammogram Registration Using Discrete Wavelet Analysis

摘要

Registration of mammograms is an essential step to increase the effectiveness of allscreening programs planned to early detect breast cancer in asymptomatic women. New tech-niques based on data fusion of different spatial views, temporal analysis or sequences followup, and multimodal data analysis, require accurate data registration: forcing spatial alignment ofimages taken from different views, at different times or from different natures. In this work wewill focus on a new technique for automatic bilateral mammograms registration. However thesame registration technique is also useful for temporal analysis of the same patient. Bilateralmammogram registration is a challenging task; the mammographic appearance of breast tissuemay vary consiaerably, because of differences in breast compression and positioning, differ-ences in imaging techniques, and changes in the breast itself; moreover, there are no clear land-marks in a mammogram, except for the nipple when it is visible. In our approach we detect theskin-line contour as a first step, we describe the contour as a chain-code, and we make a wave-let based correlation analysis, finally we get the matching of the contours. At the end we applya global affine transformation.