Format

Send to

Choose Destination
Neuroimage. 2005 Jul 1;26(3):839-51. Epub 2005 Apr 1.

Unified segmentation.

Author information

1
Wellcome Department of Imaging Neuroscience, 12 Queen Square, London, WC1N 3BG, UK. john@fil.ion.ucl.ac.uk

Abstract

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.

[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for Elsevier Science
Loading ...
Support Center