Advances in micro-calcification clusters detection in mammography

Abstract

A new mixed feature multistage false positive (FP) reduction method for micro-calcification clusters (MCCs) detection has been developed for improving the FP reduction performance. Eleven features were extracted from both spatial and morphology domains in order to describe MCCs from different perspectives. These features are grouped into three categories: gray-level description, shape description and clusters description. Two feature sets that focus on describing MCCs on every single calcification and on clustered calcifications, respectively, were combined with a back-propagation (BP) neural network with Kalman filter to obtain the best performance of FP reduction. First, nine of the eleven gray-level description and shape description features were employed with BP neural network to eliminate all the obvious FP calcifications in the image. Second, the remaining MCCs were classified into several clusters by a widely used criterion in clinical practice and then two cluster description features were added to the first feature set to eliminate the FP clusters from the remaining MCCs. The performance results of this approach were obtained using an image database of 67 real-patients mammogram images in H. Lee Moffitt Cancer Center imaging program. The proposed method successfully reduced the FP to 3.15/image, while the detection sensitivity or true positive rate improved to 97%.