Computer-aided diagnosis of mammographic images

In this paper, enhancement of mammograms and computer-aided detection of microcalcifications by multiresolution are considered. The first part deals with methods of enhancement of mammograms. A combination of these methods is proposed and make more obvious the features of the image. The second part of this paper deals with the multiscale image processing for detection of microcalcifications. The image is first decomposed into subbands by undecimated (redundant) wavelet transform, the low-frequency subband is then set to zero followed by an adaptive thresholding. The experimental results have shown good properties of the proposed method and they are comparable with the Donoho method, and even improve this one.