Application of neural network adaptive wavelets for signal representation and classification in digital mammography

We investigate the application of adaptive wavelets for the representation and classification of microcalcification signals in digitized mammograms. A class of wavelet basis functions are used to extract features from the regions of interest. These features are then used in an artificial neural network to classify the region as containing microcalcification clusters or belonging to the background parenchyma. The dilation and shift parameters of the wavelet functions are not fixed. These parameters are included in the training scheme. In this way the wavelets are adaptive to the expected shape and size of microcalcifications. The results indicate that adaptive wavelet functions may outperform the classical fixed wavelet analysis in detection of subtle microcalcification clusters.