A method of tumors detection in digital mammography
Mei Hua Xie · 2003
We develop a general method for the detection and segmentation of tumors with an analytical model. It uses a multiresolution wavelet analysis in concert with a Bayesian classifier to identify the possible tumors. The method adaptively chooses thresholds to segment tumors from the background by using a multiscale analysis of the image probability density function. A performance analysis based on a Gaussian distribution model is used to show that the proposed adaptive threshold method is effective in segmenting tumors in mammograms. Examples are presented to demonstrate the efficiency of the technique on a variety of targets.