Identification of Masses in Mammograms byImage Sub-segmentation

摘要

Mass detection in mammography is a complex and challenge problemfor digital image processing. Partitional clustering algorithms are a good alternativefor automatic detection of such elements, but have the disadvantage of having tosegment an image into a number of regions, the number of which is unknown in ad-vance, in addition to discrete approximations of the regions of interest. In this workwe use a method of image sub-segmentation to identify possible masses in mam-mography. The advantage of this method is that the number of regions to segmentthe image is a known value so the algorithm is applied only once. Additionally, thereis a parameter a that can change between 1 and 0 in a continuous way, offering thepossibility of a continuous and more accurate approximation of the region of inter-est. Finally, since the identification of masses is based on the internal similarity ofa group data, this method offers the possibility to identify such objects even from asmall number of pixels in digital images. This paper presents an illustrative exam-ple using the traditional segmentation of images and the sub-segmentation method,which highlights the potential of the alternative we propose for such problems.