Unified segmentation

被引:6593
作者
Ashburner, J [1 ]
Friston, KJ [1 ]
机构
[1] Wellcome Dept Imaging Neurosci, Funct Imaging Lab, London WC1N 3BG, England
基金
英国惠康基金;
关键词
linage registration; tissue classification; bias correction; mixture of Gaussians; tissue probability maps;
D O I
10.1016/j.neuroimage.2005.02.018
中图分类号
Q189 [神经科学];
学科分类号
071006 ;
摘要
A probabilistic framework is presented that enables image registration, tissue classification, and bias correction to be combined within the same generative model. A derivation of a log-likelihood objective function for the unified model is provided. The model is based on a mixture of Gaussians and is extended to incorporate a smooth intensity variation and nonlinear registration with tissue probability maps. A strategy for optimising the model parameters is described, along with the requisite partial derivatives of the objective function. (c) 2005 Elsevier Inc. All rights reserved.
引用
收藏
页码:839 / 851
页数:13
相关论文
共 75 条
[1]   STRUCTURAL IMAGE-RESTORATION THROUGH DEFORMABLE TEMPLATES [J].
AMIT, Y ;
GRENANDER, U ;
PICCIONI, M .
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1991, 86 (414) :376-387
[2]   Qualitative and quantitative evaluation of six algorithms for correcting intensity nonuniformity effects [J].
Arnold, JB ;
Liow, JS ;
Schaper, KA ;
Stern, JJ ;
Sled, JG ;
Shattuck, DW ;
Worth, AJ ;
Cohen, MS ;
Leahy, RM ;
Mazziotta, JC ;
Rottenberg, DA .
NEUROIMAGE, 2001, 13 (05) :931-943
[3]   Multimodal image coregistration and partitioning - A unified framework [J].
Ashburner, J ;
Friston, K .
NEUROIMAGE, 1997, 6 (03) :209-217
[4]  
Ashburner J, 2000, HUM BRAIN MAPP, V9, P212, DOI 10.1002/(SICI)1097-0193(200004)9:4<212::AID-HBM3>3.0.CO
[5]  
2-#
[6]   Voxel-based morphometry - The methods [J].
Ashburner, J ;
Friston, KJ .
NEUROIMAGE, 2000, 11 (06) :805-821
[7]   High-dimensional image registration using symmetric priors [J].
Ashburner, J ;
Andersson, JLR ;
Friston, KJ .
NEUROIMAGE, 1999, 9 (06) :619-628
[8]  
Ashburner J, 1999, HUM BRAIN MAPP, V7, P254, DOI 10.1002/(SICI)1097-0193(1999)7:4<254::AID-HBM4>3.0.CO
[9]  
2-G
[10]   Geodesic estimation for large deformation anatomical shape averaging and interpolation [J].
Avants, B ;
Gee, JC .
NEUROIMAGE, 2004, 23 :S139-S150