The microcalcifications detection of mammograms based on multi-scale space filtering and l_1 norm nearest-neighbor classifier
Minhua Liu · Journal of Circuits and Systems · 2011
The microcalcification information is an important foundation for the diagnosis of breast cancer.In order to improve the problem of true-positive and false-positive in microcalcifications detection,a novel microcalcifications detection algorithm of mammograms based on multi-scale space filtering and l1norm nearest-neighbor(l1-NN) classifier is proposed.Firstly the multi-scale salience feature images are obtained by using multi-scale space filtering for original images,then the coarse detected binary image of microcalcifications is induced via using microcalcifications segmentation method based on human visual model.,and into the l1-NN to remove the false-positive points.Simulation results demonstrate that the proposed coarse detection method can effectively detect the suspicious microcalcifications from the mammograms including low contrast images,and the following classifier has a good performance.The microcalcifications detection has higher true-positive rate and lower false-positive rate.