Optimization of MR pulse sequences for Bayesian image segmentation

Jerry Ladd Prince, Dzung Pham

Research output: Contribution to journalArticle

Abstract

A method for optimizing MR imaging pulse sequence parameters in a statistical framework is presented. Parameters are defined to be optimal when the resulting scalar images yield optimal image segmentations using Bayesian pixel classification. Thus, Bayes risk is used as the objective function to minimize. Approximations are made to give a tractable solution in a four-step procedure. A sample calculation is carried out to determine the optimal TR and flip angle for scalar SPGR imaging of the brain. Overall, this paper gives a new approach to optimize MRI pulse sequences for the specific objective of improved image segmentation.

Original languageEnglish (US)
Pages (from-to)1651-1656
Number of pages6
JournalMedical Physics
Volume22
Issue number10
DOIs
StatePublished - 1995

Fingerprint

Neuroimaging

Keywords

  • Bayesian
  • classification
  • image segmentation
  • magnetic resonance imaging
  • pulse sequences

ASJC Scopus subject areas

  • Biophysics
  • Radiology Nuclear Medicine and imaging

Cite this

Optimization of MR pulse sequences for Bayesian image segmentation. / Prince, Jerry Ladd; Pham, Dzung.

In: Medical Physics, Vol. 22, No. 10, 1995, p. 1651-1656.

Research output: Contribution to journalArticle

@article{9ad4347016494430bfbb2bd81945a0db,
title = "Optimization of MR pulse sequences for Bayesian image segmentation",
abstract = "A method for optimizing MR imaging pulse sequence parameters in a statistical framework is presented. Parameters are defined to be optimal when the resulting scalar images yield optimal image segmentations using Bayesian pixel classification. Thus, Bayes risk is used as the objective function to minimize. Approximations are made to give a tractable solution in a four-step procedure. A sample calculation is carried out to determine the optimal TR and flip angle for scalar SPGR imaging of the brain. Overall, this paper gives a new approach to optimize MRI pulse sequences for the specific objective of improved image segmentation.",
keywords = "Bayesian, classification, image segmentation, magnetic resonance imaging, pulse sequences",
author = "Prince, {Jerry Ladd} and Dzung Pham",
year = "1995",
doi = "10.1118/1.597425",
language = "English (US)",
volume = "22",
pages = "1651--1656",
journal = "Medical Physics",
issn = "0094-2405",
publisher = "AAPM - American Association of Physicists in Medicine",
number = "10",

}

TY - JOUR

T1 - Optimization of MR pulse sequences for Bayesian image segmentation

AU - Prince, Jerry Ladd

AU - Pham, Dzung

PY - 1995

Y1 - 1995

N2 - A method for optimizing MR imaging pulse sequence parameters in a statistical framework is presented. Parameters are defined to be optimal when the resulting scalar images yield optimal image segmentations using Bayesian pixel classification. Thus, Bayes risk is used as the objective function to minimize. Approximations are made to give a tractable solution in a four-step procedure. A sample calculation is carried out to determine the optimal TR and flip angle for scalar SPGR imaging of the brain. Overall, this paper gives a new approach to optimize MRI pulse sequences for the specific objective of improved image segmentation.

AB - A method for optimizing MR imaging pulse sequence parameters in a statistical framework is presented. Parameters are defined to be optimal when the resulting scalar images yield optimal image segmentations using Bayesian pixel classification. Thus, Bayes risk is used as the objective function to minimize. Approximations are made to give a tractable solution in a four-step procedure. A sample calculation is carried out to determine the optimal TR and flip angle for scalar SPGR imaging of the brain. Overall, this paper gives a new approach to optimize MRI pulse sequences for the specific objective of improved image segmentation.

KW - Bayesian

KW - classification

KW - image segmentation

KW - magnetic resonance imaging

KW - pulse sequences

UR - http://www.scopus.com/inward/record.url?scp=0028818274&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028818274&partnerID=8YFLogxK

U2 - 10.1118/1.597425

DO - 10.1118/1.597425

M3 - Article

C2 - 8551990

AN - SCOPUS:0028818274

VL - 22

SP - 1651

EP - 1656

JO - Medical Physics

JF - Medical Physics

SN - 0094-2405

IS - 10

ER -