RESUMEN
A model-based method is proposed for the measurement of breast skin thickness from digitised mammograms that takes into account both the geometric and radiographic properties of the skin region. The method initially identifies a salient feature that discriminates the skin from the other anatomical structures of the breast. Its identification is based on a multi-scale grey-level gradient estimation, using a wavelet decomposition of the image. The spatial distribution of this feature is organised as a graph, with each of its nodes associated with a binary set of interpretation labels. A Markov random field is defined on the set of labels, and the best graph labelling is finally determined with a maximum a posteriori (MAP) probability criterion. The method was applied on 11 mammograms with improved contrast characteristics at the breast periphery, obtained by an exposure equalisation technique during image acquisition. The validation of the approach was performed by calculating the root mean square (RMS) error between the detected skin thickness and manual measurements performed on each of the films. The resulting error values ranged from 0.1 mm to 0.2 mm for normal cases and reached a maximum of 0.5mm in pathological cases with advanced skin thickening.