Bayesian estimation of hyperparameters in MRI through the maximum evidence method

Bayesian inference methods are commonly applied to the classification of brain Magnetic Resonance images (MRI). We use the Maximum Evidence (ME) approach to estimate the most probable parameters and hyperparameters for models that take into account discrete classes (DM) and models accounting for the...

Descripción completa

Guardado en:
Detalles Bibliográficos
Publicado: 2008
Materias:
Bayesian networks
Color image processing
Computational geometry
Computer graphics
Digital image storage
Image enhancement
Image processing
Imaging systems
Magnetic resonance imaging
Parameter estimation
Resonance
And models
Approximate algorithms
Bayesian estimations
Bayesian inferences
Computationally expensive
Digital phantoms
Error predictions
Hyper parameters
Magnetic resonance images
Measured datums
Model optimizations
Partial volume effects
Simulated images
Inference engines
Acceso en línea:https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_97807695_v_n_p129_Oliva
http://hdl.handle.net/20.500.12110/paper_97807695_v_n_p129_Oliva
Aporte de:
Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA) de Universidad de Buenos Aires
id paper:paper_97807695_v_n_p129_Oliva
record_format dspace
spelling paper:paper_97807695_v_n_p129_Oliva2023-06-08T16:37:07Z Bayesian estimation of hyperparameters in MRI through the maximum evidence method Bayesian networks Color image processing Computational geometry Computer graphics Digital image storage Image enhancement Image processing Imaging systems Magnetic resonance imaging Parameter estimation Resonance And models Approximate algorithms Bayesian estimations Bayesian inferences Computationally expensive Digital phantoms Error predictions Hyper parameters Magnetic resonance images Measured datums Model optimizations Partial volume effects Simulated images Inference engines Bayesian inference methods are commonly applied to the classification of brain Magnetic Resonance images (MRI). We use the Maximum Evidence (ME) approach to estimate the most probable parameters and hyperparameters for models that take into account discrete classes (DM) and models accounting for the partial volume effect (PVM). An approximate algorithm was developed for model optimization, since the exact image inference calculation is computationally expensive. The method was validated using simulated images and a digital phantom. We show that the Evidence is a very useful figure for error prediction, which is to be maximized respect to the hyperparameters. Additionally, it provides a tool to determine the most probable model given measured data. © 2008 IEEE. 2008 https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_97807695_v_n_p129_Oliva http://hdl.handle.net/20.500.12110/paper_97807695_v_n_p129_Oliva
institution Universidad de Buenos Aires
institution_str I-28
repository_str R-134
collection Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA)
topic Bayesian networks
Color image processing
Computational geometry
Computer graphics
Digital image storage
Image enhancement
Image processing
Imaging systems
Magnetic resonance imaging
Parameter estimation
Resonance
And models
Approximate algorithms
Bayesian estimations
Bayesian inferences
Computationally expensive
Digital phantoms
Error predictions
Hyper parameters
Magnetic resonance images
Measured datums
Model optimizations
Partial volume effects
Simulated images
Inference engines
spellingShingle Bayesian networks
Color image processing
Computational geometry
Computer graphics
Digital image storage
Image enhancement
Image processing
Imaging systems
Magnetic resonance imaging
Parameter estimation
Resonance
And models
Approximate algorithms
Bayesian estimations
Bayesian inferences
Computationally expensive
Digital phantoms
Error predictions
Hyper parameters
Magnetic resonance images
Measured datums
Model optimizations
Partial volume effects
Simulated images
Inference engines
Bayesian estimation of hyperparameters in MRI through the maximum evidence method
topic_facet Bayesian networks
Color image processing
Computational geometry
Computer graphics
Digital image storage
Image enhancement
Image processing
Imaging systems
Magnetic resonance imaging
Parameter estimation
Resonance
And models
Approximate algorithms
Bayesian estimations
Bayesian inferences
Computationally expensive
Digital phantoms
Error predictions
Hyper parameters
Magnetic resonance images
Measured datums
Model optimizations
Partial volume effects
Simulated images
Inference engines
description Bayesian inference methods are commonly applied to the classification of brain Magnetic Resonance images (MRI). We use the Maximum Evidence (ME) approach to estimate the most probable parameters and hyperparameters for models that take into account discrete classes (DM) and models accounting for the partial volume effect (PVM). An approximate algorithm was developed for model optimization, since the exact image inference calculation is computationally expensive. The method was validated using simulated images and a digital phantom. We show that the Evidence is a very useful figure for error prediction, which is to be maximized respect to the hyperparameters. Additionally, it provides a tool to determine the most probable model given measured data. © 2008 IEEE.
title Bayesian estimation of hyperparameters in MRI through the maximum evidence method
title_short Bayesian estimation of hyperparameters in MRI through the maximum evidence method
title_full Bayesian estimation of hyperparameters in MRI through the maximum evidence method
title_fullStr Bayesian estimation of hyperparameters in MRI through the maximum evidence method
title_full_unstemmed Bayesian estimation of hyperparameters in MRI through the maximum evidence method
title_sort bayesian estimation of hyperparameters in mri through the maximum evidence method
publishDate 2008
url https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_97807695_v_n_p129_Oliva
http://hdl.handle.net/20.500.12110/paper_97807695_v_n_p129_Oliva
_version_ 1768546467702636544

Ejemplares similares