Construction of abdominal probabilistic atlases and their value in segmentation of normal organs in abdominal CT scans

Hyunjin Park, Alfred Hero, Peyton Bland, Marc Kessler, Jongbum Seo, Charles Meyer

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

A good abdominal probabilistic atlas can provide important information to guide segmentation and registration applications in the abdomen. Here we build and test probabilistic atlases using 24 abdominal CT scans with available expert manual segmentations. Atlases are built by picking a target and mapping other training scans onto that target and then summing the results into one probabilistic atlas. We improve our previous abdominal atlas by 1) choosing a least biased target as determined by a statistical tool, i.e. multidimensional scaling operating on bending energy, 2) using a better set of control points to model the deformation, and 3) using higher information content CT scans with visible internal liver structures. One atlas is built in the least biased target space and two atlases are built in other target spaces for performance comparisons. The value of an atlas is assessed based on the resulting segmentations; whichever atlas yields the best segmentation performance is considered the better atlas. We consider two segmentation methods of abdominal volumes after registration with the probabilistic atlas: 1) simple segmentation by atlas thresholding and 2) application of a Bayesian maximum a posteriori method. Using jackknifing we measure the atlas-augmented segmentation performance with respect to manual expert segmentation and show that the atlas built in the least biased target space yields better segmentation performance than atlases built in other target spaces.

Original languageEnglish
Pages (from-to)2291-2301
Number of pages11
JournalIEICE Transactions on Information and Systems
VolumeE93-D
Issue number8
DOIs
Publication statusPublished - 2010 Jan 1

Fingerprint

Computerized tomography
Liver

All Science Journal Classification (ASJC) codes

  • Software
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence
  • Electrical and Electronic Engineering

Cite this

Park, Hyunjin ; Hero, Alfred ; Bland, Peyton ; Kessler, Marc ; Seo, Jongbum ; Meyer, Charles. / Construction of abdominal probabilistic atlases and their value in segmentation of normal organs in abdominal CT scans. In: IEICE Transactions on Information and Systems. 2010 ; Vol. E93-D, No. 8. pp. 2291-2301.
@article{46155c5fbdee481eb846d5c6c1e8d25b,
title = "Construction of abdominal probabilistic atlases and their value in segmentation of normal organs in abdominal CT scans",
abstract = "A good abdominal probabilistic atlas can provide important information to guide segmentation and registration applications in the abdomen. Here we build and test probabilistic atlases using 24 abdominal CT scans with available expert manual segmentations. Atlases are built by picking a target and mapping other training scans onto that target and then summing the results into one probabilistic atlas. We improve our previous abdominal atlas by 1) choosing a least biased target as determined by a statistical tool, i.e. multidimensional scaling operating on bending energy, 2) using a better set of control points to model the deformation, and 3) using higher information content CT scans with visible internal liver structures. One atlas is built in the least biased target space and two atlases are built in other target spaces for performance comparisons. The value of an atlas is assessed based on the resulting segmentations; whichever atlas yields the best segmentation performance is considered the better atlas. We consider two segmentation methods of abdominal volumes after registration with the probabilistic atlas: 1) simple segmentation by atlas thresholding and 2) application of a Bayesian maximum a posteriori method. Using jackknifing we measure the atlas-augmented segmentation performance with respect to manual expert segmentation and show that the atlas built in the least biased target space yields better segmentation performance than atlases built in other target spaces.",
author = "Hyunjin Park and Alfred Hero and Peyton Bland and Marc Kessler and Jongbum Seo and Charles Meyer",
year = "2010",
month = "1",
day = "1",
doi = "10.1587/transinf.E93.D.2291",
language = "English",
volume = "E93-D",
pages = "2291--2301",
journal = "IEICE Transactions on Information and Systems",
issn = "0916-8532",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "8",

}

Construction of abdominal probabilistic atlases and their value in segmentation of normal organs in abdominal CT scans. / Park, Hyunjin; Hero, Alfred; Bland, Peyton; Kessler, Marc; Seo, Jongbum; Meyer, Charles.

In: IEICE Transactions on Information and Systems, Vol. E93-D, No. 8, 01.01.2010, p. 2291-2301.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Construction of abdominal probabilistic atlases and their value in segmentation of normal organs in abdominal CT scans

AU - Park, Hyunjin

AU - Hero, Alfred

AU - Bland, Peyton

AU - Kessler, Marc

AU - Seo, Jongbum

AU - Meyer, Charles

PY - 2010/1/1

Y1 - 2010/1/1

N2 - A good abdominal probabilistic atlas can provide important information to guide segmentation and registration applications in the abdomen. Here we build and test probabilistic atlases using 24 abdominal CT scans with available expert manual segmentations. Atlases are built by picking a target and mapping other training scans onto that target and then summing the results into one probabilistic atlas. We improve our previous abdominal atlas by 1) choosing a least biased target as determined by a statistical tool, i.e. multidimensional scaling operating on bending energy, 2) using a better set of control points to model the deformation, and 3) using higher information content CT scans with visible internal liver structures. One atlas is built in the least biased target space and two atlases are built in other target spaces for performance comparisons. The value of an atlas is assessed based on the resulting segmentations; whichever atlas yields the best segmentation performance is considered the better atlas. We consider two segmentation methods of abdominal volumes after registration with the probabilistic atlas: 1) simple segmentation by atlas thresholding and 2) application of a Bayesian maximum a posteriori method. Using jackknifing we measure the atlas-augmented segmentation performance with respect to manual expert segmentation and show that the atlas built in the least biased target space yields better segmentation performance than atlases built in other target spaces.

AB - A good abdominal probabilistic atlas can provide important information to guide segmentation and registration applications in the abdomen. Here we build and test probabilistic atlases using 24 abdominal CT scans with available expert manual segmentations. Atlases are built by picking a target and mapping other training scans onto that target and then summing the results into one probabilistic atlas. We improve our previous abdominal atlas by 1) choosing a least biased target as determined by a statistical tool, i.e. multidimensional scaling operating on bending energy, 2) using a better set of control points to model the deformation, and 3) using higher information content CT scans with visible internal liver structures. One atlas is built in the least biased target space and two atlases are built in other target spaces for performance comparisons. The value of an atlas is assessed based on the resulting segmentations; whichever atlas yields the best segmentation performance is considered the better atlas. We consider two segmentation methods of abdominal volumes after registration with the probabilistic atlas: 1) simple segmentation by atlas thresholding and 2) application of a Bayesian maximum a posteriori method. Using jackknifing we measure the atlas-augmented segmentation performance with respect to manual expert segmentation and show that the atlas built in the least biased target space yields better segmentation performance than atlases built in other target spaces.

UR - http://www.scopus.com/inward/record.url?scp=77956045895&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77956045895&partnerID=8YFLogxK

U2 - 10.1587/transinf.E93.D.2291

DO - 10.1587/transinf.E93.D.2291

M3 - Article

VL - E93-D

SP - 2291

EP - 2301

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

SN - 0916-8532

IS - 8

ER -