Mean field and information theoretic algorithms for direct segmentation of tomographic images

Research output: Contribution to journalConference article

Abstract

We apply the weak membrane model with optimization by mean field annealing to the direct segmentation of tomographic images. We also introduce models based on the minimum description length principle that include penalties for measurement error, boundary length, regions, and means. Outliers are prevented by upper and lower bound constraints on pixel values. Several models are generalized to three-dimensional images. The superiority of our models to convolution back projection is demonstrated experimentally.

Original languageEnglish (US)
Pages (from-to)956-963
Number of pages8
JournalProceedings of SPIE - The International Society for Optical Engineering
Volume1905
DOIs
StatePublished - Jul 29 1993
EventBiomedical Image Processing and Biomedical Visualization 1993 - San Jose, United States
Duration: Jan 31 1993Feb 5 1993

Fingerprint

Mean Field
Segmentation
Bound Constraints
Annealing
Measurement Error
Outlier
Penalty
Upper and Lower Bounds
Convolution
Membrane
Pixel
Measurement errors
penalties
convolution integrals
Projection
Model
Model-based
Three-dimensional
Optimization
projection

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Cite this

@article{0f2ee22b448a4181a6868799c8420cd3,
title = "Mean field and information theoretic algorithms for direct segmentation of tomographic images",
abstract = "We apply the weak membrane model with optimization by mean field annealing to the direct segmentation of tomographic images. We also introduce models based on the minimum description length principle that include penalties for measurement error, boundary length, regions, and means. Outliers are prevented by upper and lower bound constraints on pixel values. Several models are generalized to three-dimensional images. The superiority of our models to convolution back projection is demonstrated experimentally.",
author = "Kerfoot, {Ian B.} and Yoram Bresler and Belmont, {Andrew S.}",
year = "1993",
month = "7",
day = "29",
doi = "10.1117/12.148709",
language = "English (US)",
volume = "1905",
pages = "956--963",
journal = "Proceedings of SPIE - The International Society for Optical Engineering",
issn = "0277-786X",
publisher = "SPIE",

}

TY - JOUR

T1 - Mean field and information theoretic algorithms for direct segmentation of tomographic images

AU - Kerfoot, Ian B.

AU - Bresler, Yoram

AU - Belmont, Andrew S.

PY - 1993/7/29

Y1 - 1993/7/29

N2 - We apply the weak membrane model with optimization by mean field annealing to the direct segmentation of tomographic images. We also introduce models based on the minimum description length principle that include penalties for measurement error, boundary length, regions, and means. Outliers are prevented by upper and lower bound constraints on pixel values. Several models are generalized to three-dimensional images. The superiority of our models to convolution back projection is demonstrated experimentally.

AB - We apply the weak membrane model with optimization by mean field annealing to the direct segmentation of tomographic images. We also introduce models based on the minimum description length principle that include penalties for measurement error, boundary length, regions, and means. Outliers are prevented by upper and lower bound constraints on pixel values. Several models are generalized to three-dimensional images. The superiority of our models to convolution back projection is demonstrated experimentally.

UR - http://www.scopus.com/inward/record.url?scp=85043414360&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85043414360&partnerID=8YFLogxK

U2 - 10.1117/12.148709

DO - 10.1117/12.148709

M3 - Conference article

AN - SCOPUS:85043414360

VL - 1905

SP - 956

EP - 963

JO - Proceedings of SPIE - The International Society for Optical Engineering

JF - Proceedings of SPIE - The International Society for Optical Engineering

SN - 0277-786X

ER -