DocumentCode :
2220065
Title :
K2. Automatic pectoral muscle boundary detection in mammograms using eigenvectors segmentation
Author :
Abdellatif, H. ; Taha, T.E. ; Zahran, O.F. ; Al-Nauimy, W. ; El-Samie, F. E Abd
Author_Institution :
Fac. of Electron. Eng., Menoufia Univ., Menouf, Egypt
fYear :
2012
fDate :
10-12 April 2012
Firstpage :
633
Lastpage :
640
Abstract :
Mammograms are X-ray images, which are used in breast cancer detection. Automatic pectoral muscle removal on Medio-Lateral Oblique-view (MLO) of mammograms is an essential step for many mammography processing algorithms. Presence of pectoral muscle gives false positive results in automated breast cancer detection. The sizes, the shapes and the intensity contrasts of pectoral muscles change greatly from one MLO view to another. So, the suppression or exclusion of the pectoral muscle from the mammograms is demanded for computer-aided analysis, and this task requires the identification of the pectoral muscle. The main objective of this study is to propose an automated method to efficiently identify the pectoral muscle in MLO mammograms. This work uses a normalized graph cuts segmentation technique for identifying the pectoral muscle edge.
Keywords :
cancer; diagnostic radiography; eigenvalues and eigenfunctions; graph theory; image segmentation; mammography; medical image processing; muscle; MLO mammograms; X-ray images; automated breast cancer detection; automatic pectoral muscle boundary detection; computer aided analysis; eigenvector segmentation; intensity contrasts; mammography processing algorithms; medio lateral oblique view; Breast cancer; Educational institutions; Image edge detection; Image segmentation; Muscles; Vectors; Image segmentation; Mammograms; Normalized graph cuts; Pectoral muscle;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Radio Science Conference (NRSC), 2012 29th National
Conference_Location :
Cairo
Print_ISBN :
978-1-4673-1884-6
Type :
conf
DOI :
10.1109/NRSC.2012.6208576
Filename :
6208576
Link To Document :
بازگشت