A multiscale algorithm for segmenting calcifications from high-resolution mammographic specimen radiographs

We have developed a multiscale algorithm for segmenting breast calcifications from high-resolution specimen radiographs. The algorithm was evaluated using 152 mammographic regions of interest digitized at a 15-microm spatial resolution. The true-positive detection rate was approximately 97.4% with 0.67 false-positives per image, and the segmentation error of individual calcification particles was approximately 5%. The performance of the algorithm is highly satisfactory.