Title :
Method and algorithm for mass segmentation in mammograms based on the minimisation of energy and active contour model
Author :
El Fahssi, Khalid ; Abenaou, Abdenbi ; Jai-Andaloussi, Said ; Sekkaki, Abderrahim
Author_Institution :
Comput. Sci. Dept., Univ. of Hassan II, Casablanca, Morocco
Abstract :
Breast mass segmentation in mammography plays a crucial role in Computer-Aided Diagnosis (CAD) systems. We propose in this article a method for the segmentation of mammography images. We use a combined solution of the two approaches; one based on levels set theory and the other based on the principle of the minimization of the energy of active contours. The elaborated algorithm which is an interactive approach permits to segment effectively the images from its coarse resolution to its refinement. The results of the segmentation are illustrated from the database of MIAS.
Keywords :
image resolution; image segmentation; mammography; medical image processing; minimisation; numerical analysis; physiological models; MIAS database; active contour model; breast mass segmentation; computer-aided diagnosis systems; energy minimisation; levels set theory; mammography image resolution; mammography image segmentation; Breast; Cancer; Computers; Databases; Image segmentation; Level set; Minimization; active contours; levels set; mammography; segmentation;
Conference_Titel :
Medical Information and Communication Technology (ISMICT), 2014 8th International Symposium on
Conference_Location :
Firenze
DOI :
10.1109/ISMICT.2014.6825239