Title :
Mouse embryo’s heart segmentation on μMRI acquisitions
Author :
Zouagui, T. ; Chereul, E. ; Odet, C. ; Janier, M.
Author_Institution :
LSI, Univ. of Sci. of Oran (USTO), Oran
Abstract :
To understand the mechanisms of human development, embryologists study the development of mouse embryos. The aim of the research, as presented in this paper, is to identify cardiac malformations which are a major cause of mortallity in childhood. With this end in view, we developed expert computer based algorithms known as segmentation. The segmentation framework is based on a tru 3D deformable models rather than a slice-by-slice 2D processing. It includes both a pre-processing step and the automatic segmetation. At this point, we tested our segmentation pipeline on the left and right ventricles (LV, RV) of different mouse embryos. Results on a standard data set with 5 mM of Gadolinium and TE of 10 ms are presented and compared with the manually segmented embryonic heart model done at Animage. We present also the segmentation of an abnormal mouse ventricle and the segmentation of the heart muscle.
Keywords :
biomedical MRI; cardiology; image segmentation; medical image processing; 3D deformable model; cardiac malformation identification; computer based algorithm; mouse embryo heart segmentation; muMRI acquisition; Embryo; Heart; Mice; 3D image segmentation; MRI; cardiac images; deformable models; mesh refinement; mouse;
Conference_Titel :
Signal Processing and Its Applications, 2007. ISSPA 2007. 9th International Symposium on
Conference_Location :
Sharjah
Print_ISBN :
978-1-4244-0778-1
Electronic_ISBN :
978-1-4244-1779-8
DOI :
10.1109/ISSPA.2007.4555372