DETECTION OF MICROCALCIFICATIONS IN MAMMOGRAMS USING CONTINUOUS WAVELET TRANSFORM AND MULTISCALE PRODUCT

Early detection of breast cancer relies heavily on the accurate identification of microcalcifications in mammograms. These small, low-contrast structures are often difficult to detect visually. In this paper, we propose a method based on the Continuous Wavelet Transform(CWT)combined with the multiscale product of wavelet coefficients to enhance spatial discontinuities associated with micro calcifications. After applying a pre-processing pipeline involving three combined techniques, the method is evaluated on images from the MIAS database and from the Mother and Child Hospital of N Djamena.The results demonstrate a significant enhancement of microcalcifications, including those embedded within adipose tissue, thereby facilitating detection. The performances obtained outperform several approaches previously reported in the literature for similar image types.