Mammographic images segmentation based onchaotic map clustering algorithm

Donato Cascio, Giuseppe Raso, Francesco Fauci, Marius Iacomi, Marius Mihail Iacomi

Risultato della ricerca: Article

15 Citazioni (Scopus)

Abstract

Background:This work investigates the applicability of a novel clustering approach to the segmentation ofmammographic digital images. The chaotic map clustering algorithm is used to group together similar subsets ofimage pixels resulting in a medically meaningful partition of the mammography.Methods:The image is divided into pixels subsets characterized by a set of conveniently chosen features and eachof the corresponding points in the feature space is associated to a map. A mutual coupling strength between themaps depending on the associated distance between feature space points is subsequently introduced. On thesystem of maps, the simulated evolution through chaotic dynamics leads to its natural partitioning, whichcorresponds to a particular segmentation scheme of the initial mammographic image.Results:The system provides a high recognition rate for small mass lesions (about 94% correctly segmented insidethe breast) and the reproduction of the shape of regions with denser micro-calcifications in about 2/3 of the cases,while being less effective on identification of larger mass lesions.Conclusions:We can summarize our analysis by asserting that due to the particularities of the mammographicimages, the chaotic map clustering algorithm should not be used as the sole method of segmentation. It is ratherthe joint use of this method along with other segmentation techniques that could be successfully used forincreasing the segmentation performance and for providing extra information for the subsequent analysis stagessuch as the classification of the segmented ROI.Keywords:Chaotic maps, Clustering algorithms, Cooperative behavior, Segmentation, Mammography, Features,Mass lesions, Microcalcifications, Breast cancer
Lingua originaleEnglish
pagine (da-a)1-11
Numero di pagine11
RivistaBMC Medical Imaging
Volume14
Stato di pubblicazionePublished - 2014

    Fingerprint

All Science Journal Classification (ASJC) codes

  • Radiology Nuclear Medicine and imaging

Cita questo