Segmentation and feature extraction for reliable classification of microcalcifications in digital mammograms

Microcalcifications are one of more important signs enabling detection of breast cancer at early stage. The main goal of the research was designing and realization of a system for automatic detection and classification of microcalcifications, taking advantage of proposed automatic feature selection algorithm. The first step of the detection algorithm is to segment the individual objects: potential microcalcifications. This is achieved by applying opening by reconstruction top-hat technique and image thresholding based on approximation of an image local histogram with a probability density function of Gauss distribution. Selected features of the segmented objects are used as inputs to neural networks. The first classifier verifies the initial detection and the others assess a diagnosis of the input objects. The algorithm results are locations of suggested microcalcifications and optionally automatic diagnosis. The presented form of the system was verified in clinical tests using diagnosed databases (DDSM from University of South Florida and own digitized database of mammograms ). Achieved results are promising, comparable with other known systems. Efficiency of microcalcifications detection was up to 90%.