Title :
Left ventricular segmentation in MRI images
Author :
Cassen, C. ; Domenger, J.P. ; Braquelaire, J.P. ; Barat, J.L.
Author_Institution :
LaBRI, Bordeaux I Univ., Talence, France
Abstract :
We present an original method for segmentation of the left ventricle from time varying cross-sectional slices. This segmentation method is based on a split and merge algorithm. The endocardial and the epicardial contours in the first image of the sequence are drawn manually, the other contours of the sequence are computed automatically. This algorithm integrates the topological and geometrical characteristics of the left ventricle over time. This method is robust despite noise, artifacts and time varying contrast
Keywords :
biomedical MRI; cardiology; geometry; image segmentation; image sequences; topology; MRI images; artifacts; endocardial contours; epicardial contours; geometrical characteristics; left ventricular segmentation; noise; split-and-merge algorithm; time varying contrast; time varying cross-sectional slices; topological characteristics; Active contours; Blood flow; Cows; Heart; Image resolution; Image segmentation; Magnetic resonance imaging; Muscles; Noise robustness; Spatial resolution;
Conference_Titel :
Image and Signal Processing and Analysis, 2001. ISPA 2001. Proceedings of the 2nd International Symposium on
Conference_Location :
Pula
Print_ISBN :
953-96769-4-0
DOI :
10.1109/ISPA.2001.938635
