Susan M. Astley et al. (Eds.): IWDM 2006, LNCS 4046, pp. 549 – 556, 2006. © Springer-Verlag Berlin Heidelberg 2006 Breast Component Adaptive Wavelet Enhancement for Soft-Copy Display of Mammograms Spyros Skiadopoulos, Anna Karahaliou, Filippos Sakellaropoulos, George Panayiotakis, and Lena Costaridou Department of Medical Physics, School of Medicine, University of Patras, 265 00 Patras, Greece costarid@upatras.gr, panayiot@upatras.gr Abstract. A method that performs multiresolution enhancement, adaptive to breast components, for optimal visualization of the entire breast area is presented. The method includes an edge detection step to distinguish breast area from mammogram background and employs Gaussian mixture modeling to segment breast components (uncompressed fat, fat and dense). The original image is decomposed using a redundant discrete wavelet transform and magnitude coefficients corresponding to each breast component are linearly mapped for contrast enhancement. Coefficient mapping is controlled by a gain factor provided by the parameters of the modeled breast components. The processed image is derived by reconstruction of the modified wavelet coefficients. The algorithm is compared with two enhancement methods proposed for soft-copy display, in a dataset of 68 mammograms containing lesions. The proposed method demonstrates increased performance in accentuating lesions embedded in fatty or dense parenchyma, as well as in visualization of anatomical features in the entire breast area. 1 Background Screen film mammography is the primary imaging technique for the detection and diagnosis of breast lesions. However, the high diagnostic performance of screen film mammography is challenged by occult disease signs (microcalcifications and/or masses) due to the masking effect of dense breast parenchyma, and the over-exposure of breast periphery. Several computer-based algorithms have been proposed to enhance subtle features of interest in digital and digitized mammograms [1], [2]. These methods can be classified according to the type of processing used (global/locally-adaptive histogram equalization, region or neighborhood adaptive enhancement and wavelet enhance- ment) and to target area (dense tissue and/or breast periphery). In the advent of Full Field Digital Mammography (FFDM), it is crucial to exploit the potential of image processing algorithms in enhancing the ability of radiologists to interpret images [1], [2]. To be eligible, candidate methods should also fulfill functionality requirements of robustness and computational speed for soft-copy display.