DocumentCode :
3505608
Title :
Atlas construction from high angular resolution diffusion imaging data represented by Gaussian Mixture fields
Author :
Cheng, Guang ; Vemuri, Baba C. ; Hwang, Min-Sig ; Howland, Dena ; Forder, John R.
Author_Institution :
Dept. of CISE, Univ. of Florida, Gainesville, FL, USA
fYear :
2011
fDate :
March 30 2011-April 2 2011
Firstpage :
549
Lastpage :
552
Abstract :
Groupwise image registration is an essential part of atlas construction which is a very import and challenging task in medical image analysis. In this paper, we present a novel atlas construction technique using a groupwise registration of high angular resolution diffusion (MR) imaging datasets each of which is represented by a Gaussian Mixture field. To solve the registration problem, an L2 distance is used to measure the similarity between two Gaussian Mixtures, which leads to an energy function whosegradient can be computed in closed form. A projection method is developed to construct a “sharp” (not blurred) atlas from the result of this groupwise registration. Synthetic and real data experiments are presented to demonstrate the efficacy of the proposed method.
Keywords :
biomedical MRI; image registration; medical image processing; Gaussian mixture fields; Gaussian mixture similarity; L2 distance; atlas construction technique; energy function gradient; groupwise image registration; high angular resolution diffusion MRI data; high angular resolution diffusion imaging data; medical image analysis; projection method; Diffusion tensor imaging; Equations; Estimation; Image registration; Image resolution; Tensile stress; Atlas Construction; Gaussian Mixture Fields; Groupwise registration; HARDI;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Biomedical Imaging: From Nano to Macro, 2011 IEEE International Symposium on
Conference_Location :
Chicago, IL
ISSN :
1945-7928
Print_ISBN :
978-1-4244-4127-3
Electronic_ISBN :
1945-7928
Type :
conf
DOI :
10.1109/ISBI.2011.5872466
Filename :
5872466
Link To Document :
بازگشت