Background: This work investigates the applicability of a novel clustering approach to the segmentation of\nmammographic digital images. The chaotic map clustering algorithm is used to group together similar subsets of\nimage pixels resulting in a medically meaningful partition of the mammography.\nMethods: The image is divided into pixels subsets characterized by a set of conveniently chosen features and each\nof the corresponding points in the feature space is associated to a map. A mutual coupling strength between the\nmaps depending on the associated distance between feature space points is subsequently introduced. On the\nsystem of maps, the simulated evolution through chaotic dynamics leads to its natural partitioning, which\ncorresponds to a particular segmentation scheme of the initial mammographic image.\nResults: The system provides a high recognition rate for small mass lesions (about 94% correctly segmented inside\nthe breast) and the reproduction of the shape of regions with denser micro-calcifications in about 2/3 of the cases,\nwhile being less effective on identification of larger mass lesions.\nConclusions: We can summarize our analysis by asserting that due to the particularities of the mammographic\nimages, the chaotic map clustering algorithm should not be used as the sole method of segmentation. It is rather\nthe joint use of this method along with other segmentation techniques that could be successfully used for\nincreasing the segmentation performance and for providing extra information for the subsequent analysis stages\nsuch as the classification of the segmented ROI.
Loading....