DocumentCode :
2374939
Title :
Shape-aided kidney extraction in MR urography
Author :
Tang, Yang ; Jackson, Hollie ; Lee, Susan ; Nelson, Marvin ; Moats, Rex A.
Author_Institution :
Dept. of Radiol., Univ. of Southern California, Los Angeles, CA, USA
fYear :
2009
fDate :
3-6 Sept. 2009
Firstpage :
5781
Lastpage :
5784
Abstract :
MR Urography (MRU) plays an important role in pediatric renal diagnoses. While accurate measurement of the kidney is essential for each imaging study, it is challenging to extract the kidney from its background. In this paper, we propose a co-focus elliptical kidney model (CEKM) to integrate the shape prior and build a novel extraction method with both regional and edge information. With a similarity metric defined between a binary mask and CEKM, a kidney template can be obtained using optimization technique. Then, a shape term derived from a distance and orientation description is designed to modify an active contour model. The distance map is used to control the contours in terms of CEKM and orientation map is designed to reduce the artifacts resulting from fake edges. The final kidney was determined with iterative solution. With the priori shape description in a parametric space, the new method can precisely extract the kidney without training, and supply promising results as the experiments demonstrated.
Keywords :
biomedical MRI; edge detection; feature extraction; medical image processing; MR Urography; active contour model; binary mask; cofocus elliptical kidney model; edge image information; pediatric renal diagnosis; regional image information; shape aided kidney extraction; Algorithms; Artificial Intelligence; Humans; Image Enhancement; Image Interpretation, Computer-Assisted; Kidney; Magnetic Resonance Imaging; Pattern Recognition, Automated; Reproducibility of Results; Sensitivity and Specificity; Urography;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Engineering in Medicine and Biology Society, 2009. EMBC 2009. Annual International Conference of the IEEE
Conference_Location :
Minneapolis, MN
ISSN :
1557-170X
Print_ISBN :
978-1-4244-3296-7
Electronic_ISBN :
1557-170X
Type :
conf
DOI :
10.1109/IEMBS.2009.5332537
Filename :
5332537
Link To Document :
بازگشت