Affordable Access

Unified segmentation.

Authors
  • Ashburner, John
  • Friston, Karl J
Type
Published Article
Journal
NeuroImage
Publication Date
Jul 01, 2005
Volume
26
Issue
3
Pages
839–851
Identifiers
PMID: 15955494
Source
Medline
License
Unknown

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.

Report this publication

Statistics

Seen <100 times