DocumentCode :
2571819
Title :
Fully automatic segmentation of the dentate nucleus using diffusion weighted images
Author :
Ye, Chuyang ; Bogovic, John A. ; Bazin, Pierre-Louis ; Prince, Jerry L. ; Ying, Sarah H.
Author_Institution :
Dept. of Electr. & Comput. Eng., Johns Hopkins Univ., Baltimore, MD, USA
fYear :
2012
fDate :
2-5 May 2012
Firstpage :
1128
Lastpage :
1131
Abstract :
We propose a fully automatic method to segment the dentate nucleus using diffusion weighted images (DWI). Initialization of the dentate nucleus is produced by combining the information from tractography results on the diffusion tensor images (reconstructed from DWI) and b0 images. A geometric de-formable model (GDM) with generalized gradient vector flow (GGVF) is then applied on the b0 image to generate the segmentation by evolving the level set function. Experiments have been carried out on real data and quantitative comparison shows that our segmentation results agree well with expert manual delineations and produce accurate results.
Keywords :
biodiffusion; biomedical MRI; image reconstruction; image segmentation; medical image processing; dentate nucleus; diffusion tensor images; diffusion weighted images; expert manual delineations; fully automatic segmentation; generalized gradient vector flow; geometric deformable model; image reconstruction; level set function; tractography; Diffusion tensor imaging; Force; Humans; Image edge detection; Image segmentation; Level set; Manuals; dentate nucleus; diffusion weighted images; generalized gradient vector flow; geometric deformable model; segmentation;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Biomedical Imaging (ISBI), 2012 9th IEEE International Symposium on
Conference_Location :
Barcelona
ISSN :
1945-7928
Print_ISBN :
978-1-4577-1857-1
Type :
conf
DOI :
10.1109/ISBI.2012.6235758
Filename :
6235758
Link To Document :
بازگشت