New range-based neighbourhood operator for extracting edge and texture information from mammograms for subsequent image segmentation and analysis

A new, spatially isotropic, range-based, neighbourhood operator is describe d, and its use for extracting edge and texture information from mammograms is illustrated. It is an extension of an operator, first introduced by J.C. Russ, and founded on the work of H.E. Hurst. An octagonal neighbourhood is defined, centred on each pixel in an image, and the difference between the maximum and minimum pixel values in each set of pixels at a given Euclidea n distance from the centre pixel is computed to be the range. The logarithm of the range is plotted against the logarithm of the distance, and a strai ght line fitted to the data. The y-axis intercept and the square of the cor relation coefficient, eta (2), are associated with the position of the cent re pixel. Preliminary experiments suggest that is edge-sensitive and could be useful in detecting weak edges, with good noise immunity, while eta (2) is a promising texture measure that may be used to detect the edge of the p ectoral muscle, define the boundary of the mammographic parenchyma, and in conjunction with other features, possibly detect circumscribed lesions.