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.
Keywords
Artificial intelligenceComputer scienceProbabilistic logicSegmentationLikelihood functionGenerative modelMixture modelPattern recognition (psychology)Function (biology)Nonlinear systemImage segmentationImage (mathematics)Generative grammarAlgorithmMathematicsEstimation theory
MeSH Terms
AlgorithmsBrain MappingData InterpretationStatisticalFuzzy LogicImage ProcessingComputer-AssistedLikelihood FunctionsMagnetic Resonance ImagingModelsNeurologicalModelsStatisticalNonlinear DynamicsNormal DistributionProbability Theory
Affiliated Institutions
Related Publications
Training Products of Experts by Minimizing Contrastive Divergence
It is possible to combine multiple latent-variable models of the same data by multiplying their probability distributions together and then renormalizing. This way of combining ...
Region competition: unifying snakes, region growing, energy/Bayes/MDL for multi-band image segmentation
We present a novel statistical and variational approach to image segmentation based on a new algorithm named region competition. This algorithm is derived by minimizing a genera...
Object class recognition by unsupervised scale-invariant learning
We present a method to learn and recognize object class models from unlabeled and unsegmented cluttered scenes in a scale invariant manner. Objects are modeled as flexible const...
Deep convolutional neural fields for depth estimation from a single image
We consider the problem of depth estimation from a sin- gle monocular image in this work. It is a challenging task as no reliable depth cues are available, e.g., stereo corre- s...
A Bayesian Morphometry Algorithm
Most methods for structure-function analysis of the brain in medical images are usually based on voxel-wise statistical tests performed on registered magnetic resonance (MR) ima...
Publication Info
- Year
- 2005
- Type
- article
- Volume
- 26
- Issue
- 3
- Pages
- 839-851
- Citations
- 7269
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
7269
OpenAlex
350
Influential
7047
CrossRef
Cite This
John Ashburner,
Karl Friston
(2005).
Unified segmentation.
NeuroImage
, 26
(3)
, 839-851.
https://doi.org/10.1016/j.neuroimage.2005.02.018
Identifiers
- DOI
- 10.1016/j.neuroimage.2005.02.018
- PMID
- 15955494