Maximum Evidence Method for classification of brain tissues in MRI

Within the family of statistical image segmentation methods, those based on Bayesian inference have been commonly applied to classify brain tissues as obtained with Magnetic Resonance Imaging (MRI). In this framework we present an unsupervised algorithm to account for the main tissue classes that co...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Isoardi, R.A., Oliva, D.E., Mato, G.
Formato: JOUR
Materias:
Bayesian estimation
Image segmentation
Magnetic Resonance Imaging
Partial volume effect
Approximate algorithms
Bayesian estimations
Bayesian inference
Brain phantoms
Brain tissue
Brain volume
Discrete models
Error prediction
Figure of merit
Mean absolute error
Measured data
Model optimization
MR images
Partial volumes
Single voxel
Statistical image segmentation
Unsupervised algorithms
Bayesian networks
Brain
Histology
Inference engines
Probability density function
Resonance
Three dimensional
Tissue
Magnetic resonance imaging
Acceso en línea:http://hdl.handle.net/20.500.12110/paper_01678655_v32_n1_p12_Isoardi
Aporte de:
Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA) de Universidad de Buenos Aires
id todo:paper_01678655_v32_n1_p12_Isoardi
record_format dspace
spelling todo:paper_01678655_v32_n1_p12_Isoardi2023-10-03T15:05:26Z Maximum Evidence Method for classification of brain tissues in MRI Isoardi, R.A. Oliva, D.E. Mato, G. Bayesian estimation Image segmentation Magnetic Resonance Imaging Partial volume effect Approximate algorithms Bayesian estimations Bayesian inference Brain phantoms Brain tissue Brain volume Discrete models Error prediction Figure of merit Mean absolute error Measured data Model optimization MR images Partial volume effect Partial volumes Single voxel Statistical image segmentation Unsupervised algorithms Bayesian networks Brain Histology Image segmentation Inference engines Probability density function Resonance Three dimensional Tissue Magnetic resonance imaging Within the family of statistical image segmentation methods, those based on Bayesian inference have been commonly applied to classify brain tissues as obtained with Magnetic Resonance Imaging (MRI). In this framework we present an unsupervised algorithm to account for the main tissue classes that constitute MR brain volumes. Two models are examined: the Discrete Model (DM), in which every voxel belongs to a single tissue class, and the Partial Volume Model (PVM), where two classes may be present in a single voxel with a certain probability. We make use of the Maximum Evidence (ME) criterion to estimate the most probable parameters describing each model in a separate fashion. Since an exact image inference would be computationally very expensive, we propose an approximate algorithm for model optimization. Such method was tested on a simulated MRI-T1 brain phantom in 3D, as well as on clinical MR images. As a result, we found that the PVM slightly outperforms the DM, both in terms of Evidence and Mean Absolute Error (MAE). We also show that the Evidence is a very useful figure of merit for error prediction as well as a convenient tool to determine the most probable model from measured data. © 2009 Elsevier B.V. All rights reserved. Fil:Oliva, D.E. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales; Argentina. JOUR info:eu-repo/semantics/openAccess http://creativecommons.org/licenses/by/2.5/ar http://hdl.handle.net/20.500.12110/paper_01678655_v32_n1_p12_Isoardi
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 estimation
Image segmentation
Magnetic Resonance Imaging
Partial volume effect
Approximate algorithms
Bayesian estimations
Bayesian inference
Brain phantoms
Brain tissue
Brain volume
Discrete models
Error prediction
Figure of merit
Mean absolute error
Measured data
Model optimization
MR images
Partial volume effect
Partial volumes
Single voxel
Statistical image segmentation
Unsupervised algorithms
Bayesian networks
Brain
Histology
Image segmentation
Inference engines
Probability density function
Resonance
Three dimensional
Tissue
Magnetic resonance imaging
spellingShingle Bayesian estimation
Image segmentation
Magnetic Resonance Imaging
Partial volume effect
Approximate algorithms
Bayesian estimations
Bayesian inference
Brain phantoms
Brain tissue
Brain volume
Discrete models
Error prediction
Figure of merit
Mean absolute error
Measured data
Model optimization
MR images
Partial volume effect
Partial volumes
Single voxel
Statistical image segmentation
Unsupervised algorithms
Bayesian networks
Brain
Histology
Image segmentation
Inference engines
Probability density function
Resonance
Three dimensional
Tissue
Magnetic resonance imaging
Isoardi, R.A.
Oliva, D.E.
Mato, G.
Maximum Evidence Method for classification of brain tissues in MRI
topic_facet Bayesian estimation
Image segmentation
Magnetic Resonance Imaging
Partial volume effect
Approximate algorithms
Bayesian estimations
Bayesian inference
Brain phantoms
Brain tissue
Brain volume
Discrete models
Error prediction
Figure of merit
Mean absolute error
Measured data
Model optimization
MR images
Partial volume effect
Partial volumes
Single voxel
Statistical image segmentation
Unsupervised algorithms
Bayesian networks
Brain
Histology
Image segmentation
Inference engines
Probability density function
Resonance
Three dimensional
Tissue
Magnetic resonance imaging
description Within the family of statistical image segmentation methods, those based on Bayesian inference have been commonly applied to classify brain tissues as obtained with Magnetic Resonance Imaging (MRI). In this framework we present an unsupervised algorithm to account for the main tissue classes that constitute MR brain volumes. Two models are examined: the Discrete Model (DM), in which every voxel belongs to a single tissue class, and the Partial Volume Model (PVM), where two classes may be present in a single voxel with a certain probability. We make use of the Maximum Evidence (ME) criterion to estimate the most probable parameters describing each model in a separate fashion. Since an exact image inference would be computationally very expensive, we propose an approximate algorithm for model optimization. Such method was tested on a simulated MRI-T1 brain phantom in 3D, as well as on clinical MR images. As a result, we found that the PVM slightly outperforms the DM, both in terms of Evidence and Mean Absolute Error (MAE). We also show that the Evidence is a very useful figure of merit for error prediction as well as a convenient tool to determine the most probable model from measured data. © 2009 Elsevier B.V. All rights reserved.
format JOUR
author Isoardi, R.A.
Oliva, D.E.
Mato, G.
author_facet Isoardi, R.A.
Oliva, D.E.
Mato, G.
author_sort Isoardi, R.A.
title Maximum Evidence Method for classification of brain tissues in MRI
title_short Maximum Evidence Method for classification of brain tissues in MRI
title_full Maximum Evidence Method for classification of brain tissues in MRI
title_fullStr Maximum Evidence Method for classification of brain tissues in MRI
title_full_unstemmed Maximum Evidence Method for classification of brain tissues in MRI
title_sort maximum evidence method for classification of brain tissues in mri
url http://hdl.handle.net/20.500.12110/paper_01678655_v32_n1_p12_Isoardi
work_keys_str_mv AT isoardira maximumevidencemethodforclassificationofbraintissuesinmri
AT olivade maximumevidencemethodforclassificationofbraintissuesinmri
AT matog maximumevidencemethodforclassificationofbraintissuesinmri
_version_ 1782030284102828032

Ejemplares similares