Segmentation of 4D MR renography images using temporal dynamics in a level set framework

Author

Ting Song ; Lee, V.S. ; Rusinek, H. ; Bokacheva, L. ; Laine, Andrew

Author_Institution

Dept. of Biomed. Eng., Columbia Univ., New York, NY

fYear

2008

fDate

14-17 May 2008

Firstpage

37

Lastpage

40

Abstract

A novel 4D level set framework was developed to segment dynamic MR images into the cortex, medulla and collecting system. The novelty of the method is that it combines information from spatial anatomical structures and temporal dynamics. The accuracy of the fully automatic 4D level set algorithm was found to be comparable to manual segmentation performed by experts on renal anatomy. The algorithm requires less than one minute to automatically segment a single kidney 4D patient data set with more than 40 time points.

Keywords

biomedical MRI; image segmentation; kidney; medical image processing; 4D level set framework; MR renography; collecting system; cortex; image segmentation; kidney; medulla; renal anatomy; spatial anatomical structures; Anatomical structure; Anatomy; Biomedical engineering; Biomedical imaging; Brain modeling; Data mining; Image segmentation; Level set; Magnetic resonance imaging; Radiology; MR renography; dynamic contrast enhanced MRI; image segmentation; level set; temporal dynamics;

fLanguage

English

Publisher

ieee

Conference_Titel

Biomedical Imaging: From Nano to Macro, 2008. ISBI 2008. 5th IEEE International Symposium on

Conference_Location

Paris

Print_ISBN

978-1-4244-2002-5

Electronic_ISBN

978-1-4244-2003-2

Type

conf

DOI

10.1109/ISBI.2008.4540926

Filename

4540926