Detection of microcalcifications by means of multiscale methods and statistical techniques

The detection of clustered microcalcifications can help the radiologist to detect early breast cancer. Microcalcifications exhibit some important char acteristics, such as small size and high luminosity. Use of a computer-aide d diagnosis (CAD) method can prevent them being overlooked. In this report, a multiresolution analysis is performed based on a multilevel wavelet tran sformation. Decomposition produces sub-band images which become visible onl y as details of the different scales. Thereafter, all the images will be co mbined in a final image, in order to obtain an image that contains all the interest details at the scale where microcalcifications tend to appear. Onc e the image, called detail image, is obtained, it is necessary to determine which details correspond with microcalcifications. Statistical analysis of the histogram permits classification of the zones likely to contain microc alcifications. Applying this statistical techniques over the whole image an d representing the results in a two-dimensional map, clustered microcalcifi cation regions are clearly distinguishable. Copyright (C) 2000 by W.B. Saun ders Company.