The detection and classification of microcalcifications in the visibility-enhanced mammograms obtained by using the pixel assignment-based spatial filter

Abstract

In this paper, we proposed a computer aided diagnosis (CAD) system which has the pixel assignment-based a spatial filter to enhance the visibility of microcalcifications in mammograms. This filter first sums the absolute values of the differences between the center pixel-of-interest and its 8-neighbors, and then assigns this summed value to that center pixel-of-interest. This process was repeated for each pixel of all images, and the contrast stretching was applied into all obtained images. Then, it was firstly detected by using different classifiers whether is absent/present of microcalcification in the obtained images, and the detected microcalcifications were classified as benign/malignant by using the same classifiers. In order to evaluate the effects of the proposed filter on the detection and classification successes, it was compared to widely used filters. In the implemented experiments, this comparison showed that the proposed filter provided higher contribution to the detection and classification successes than the others, and hence enhanced the visibility of microcalcifications in mammograms. Finally, it can be concluded that the CAD system with the proposed filter can contribute to the development of the state-of-art methodologies and can be used as a diagnostic decision support mechanism in the analysis of mammograms.