A method of tumors detection in digital mammography

摘要

A genera] method for the detection and segmentation of tumors is developed in this paper. We develop an analytic model for the segmentation of tumors, which uses a multiresolution analysis in conceit with a Bayesian classifier to identify the possible tumors. The method is developed which adaptively chooses thresholds to segment tumors from 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. Examples are presented to demonstrate the efficiency of the technique on a variety of targets.