Wavelets investigation for computer aided detection of microcalcification in breast cancer

Breast cancer can be diagnosed with an early training course by detecting the presence of microcalcifications in screening mammograms. 2D wavelet transform decomposition is widely used in computer aided detection of microcalcifications in mammograms. The aim of this work is to investigate the better type of wavelet and its optimal potential level of decomposition that gives us better detection. Our approach is divided into two phases. The first phase of our algorithm consists on multiresolution analysis based on 1D discrete wavelet transform over profiles of microcalcifications extracted from mammographic images. This analysis is carried out with several families of wavelets. The second phase of our algorithm is interested in the validation of the results of the first. In this stage, we apply 2D discrete wavelet transform in analysis and synthesis on screening mammograms extracted from the MIAS MiniMammographic database (Mammographic Image Analysis Society) in order to detect the microcalcifications.