Title :
Mass segmantation on mammograms using active contours
Author :
Tunali, I. ; Kilic, E.
Author_Institution :
Bilgisayar Muhendisligi Bolumu, Ondokuz Mayis Univ., Samsun, Turkey
Abstract :
In this paper segmentation of benign and malignant masses found on mammograms were segmented. After adding low valued pixels outside of mammogram, Chan-Vese active contour algorithm with a new stopping criteria was implemented. As a result, lacking segmentation was prevented. Experiments were made on 60 mammograms which had masses with different shape, size and visibility taken from Digital Database for Screening Mammography(DDSM). Proposed method had a Area Overlap Ratio of %75.1.
Keywords :
image segmentation; mammography; medical image processing; Chan-Vese active contour algorithm; DDSM; area overlap ratio; benign mass segmentation; digital database for screening mammography; malignant mass segmentation; mammogram; Active contours; Cancer; Capacitance-voltage characteristics; Computational modeling; Delta-sigma modulation; Histograms; Image segmentation; Mass segmentation; active contours; mammogram;
Conference_Titel :
Signal Processing and Communications Applications Conference (SIU), 2013 21st
Conference_Location :
Haspolat
Print_ISBN :
978-1-4673-5562-9
Electronic_ISBN :
978-1-4673-5561-2
DOI :
10.1109/SIU.2013.6531221
