An EM approach to MAP solution of segmenting tissue mixture percentages with application to CT-based virtual colonoscopy

Su Wang, Lihong Li, Harris Cohen, Seth Mankes, John J. Chen, Zhengrong Liang

Research output: Contribution to journalArticle

46 Citations (Scopus)

Abstract

Electronic colon cleansing (ECC) is an emerging technique developed to segment the colon lumen from a patient's abdominal computed tomography colonography (CTC) images. However, the residue stool and fluid tagged by contrast materials as well as mixed tissue distribution with partial volume (PV) effect impose several challenges for ECC, resulting in incomplete and overcomplete cleansings. To address the PV effect, this work investigated an improved maximum a posteriori expectation-maximization (MAP-EM) image segmentation algorithm which simultaneously estimates tissue mixture percentages within each image voxel and statistical model parameters for the tissue distribution. Given the segmented tissue mixture information beyond the image voxel level, not only the PV effect has been satisfactorily addressed as a particular case of tissue mixture problem, but incomplete and overcomplete ECC causes could also be maximally avoided. For clinical application to CTC that involves several issues transferring from theoretical analysis to practical validation, an innovative initialization procedure and refined estimation strategy were proposed to build an ECC pipeline based on the MAP-EM segmentation. The pipeline was evaluated based on 52 patient CTC studies, downloaded from the website of the Virtual Colonoscopy Screening Resource Center, by two radiologists. A noticeable improvement over the authors' previous ECC pipeline was documented. Several typical cases were also presented to show visually the improved performance of the presented ECC pipeline.

Original languageEnglish (US)
Pages (from-to)5787-5798
Number of pages12
JournalMedical physics
Volume35
Issue number12
DOIs
StatePublished - Jan 1 2008
Externally publishedYes

Fingerprint

Computed Tomographic Colonography
Colon
Tomography
Tissue Distribution
Statistical Models
MAP solution
Contrast Media

All Science Journal Classification (ASJC) codes

  • Biophysics
  • Radiology Nuclear Medicine and imaging

Cite this

An EM approach to MAP solution of segmenting tissue mixture percentages with application to CT-based virtual colonoscopy. / Wang, Su; Li, Lihong; Cohen, Harris; Mankes, Seth; Chen, John J.; Liang, Zhengrong.

In: Medical physics, Vol. 35, No. 12, 01.01.2008, p. 5787-5798.

Research output: Contribution to journalArticle

Wang, Su ; Li, Lihong ; Cohen, Harris ; Mankes, Seth ; Chen, John J. ; Liang, Zhengrong. / An EM approach to MAP solution of segmenting tissue mixture percentages with application to CT-based virtual colonoscopy. In: Medical physics. 2008 ; Vol. 35, No. 12. pp. 5787-5798.
@article{ce50c21ebc214f9b8d0b6bbfbd6a42a4,
title = "An EM approach to MAP solution of segmenting tissue mixture percentages with application to CT-based virtual colonoscopy",
abstract = "Electronic colon cleansing (ECC) is an emerging technique developed to segment the colon lumen from a patient's abdominal computed tomography colonography (CTC) images. However, the residue stool and fluid tagged by contrast materials as well as mixed tissue distribution with partial volume (PV) effect impose several challenges for ECC, resulting in incomplete and overcomplete cleansings. To address the PV effect, this work investigated an improved maximum a posteriori expectation-maximization (MAP-EM) image segmentation algorithm which simultaneously estimates tissue mixture percentages within each image voxel and statistical model parameters for the tissue distribution. Given the segmented tissue mixture information beyond the image voxel level, not only the PV effect has been satisfactorily addressed as a particular case of tissue mixture problem, but incomplete and overcomplete ECC causes could also be maximally avoided. For clinical application to CTC that involves several issues transferring from theoretical analysis to practical validation, an innovative initialization procedure and refined estimation strategy were proposed to build an ECC pipeline based on the MAP-EM segmentation. The pipeline was evaluated based on 52 patient CTC studies, downloaded from the website of the Virtual Colonoscopy Screening Resource Center, by two radiologists. A noticeable improvement over the authors' previous ECC pipeline was documented. Several typical cases were also presented to show visually the improved performance of the presented ECC pipeline.",
author = "Su Wang and Lihong Li and Harris Cohen and Seth Mankes and Chen, {John J.} and Zhengrong Liang",
year = "2008",
month = "1",
day = "1",
doi = "10.1118/1.3013591",
language = "English (US)",
volume = "35",
pages = "5787--5798",
journal = "Medical Physics",
issn = "0094-2405",
publisher = "AAPM - American Association of Physicists in Medicine",
number = "12",

}

TY - JOUR

T1 - An EM approach to MAP solution of segmenting tissue mixture percentages with application to CT-based virtual colonoscopy

AU - Wang, Su

AU - Li, Lihong

AU - Cohen, Harris

AU - Mankes, Seth

AU - Chen, John J.

AU - Liang, Zhengrong

PY - 2008/1/1

Y1 - 2008/1/1

N2 - Electronic colon cleansing (ECC) is an emerging technique developed to segment the colon lumen from a patient's abdominal computed tomography colonography (CTC) images. However, the residue stool and fluid tagged by contrast materials as well as mixed tissue distribution with partial volume (PV) effect impose several challenges for ECC, resulting in incomplete and overcomplete cleansings. To address the PV effect, this work investigated an improved maximum a posteriori expectation-maximization (MAP-EM) image segmentation algorithm which simultaneously estimates tissue mixture percentages within each image voxel and statistical model parameters for the tissue distribution. Given the segmented tissue mixture information beyond the image voxel level, not only the PV effect has been satisfactorily addressed as a particular case of tissue mixture problem, but incomplete and overcomplete ECC causes could also be maximally avoided. For clinical application to CTC that involves several issues transferring from theoretical analysis to practical validation, an innovative initialization procedure and refined estimation strategy were proposed to build an ECC pipeline based on the MAP-EM segmentation. The pipeline was evaluated based on 52 patient CTC studies, downloaded from the website of the Virtual Colonoscopy Screening Resource Center, by two radiologists. A noticeable improvement over the authors' previous ECC pipeline was documented. Several typical cases were also presented to show visually the improved performance of the presented ECC pipeline.

AB - Electronic colon cleansing (ECC) is an emerging technique developed to segment the colon lumen from a patient's abdominal computed tomography colonography (CTC) images. However, the residue stool and fluid tagged by contrast materials as well as mixed tissue distribution with partial volume (PV) effect impose several challenges for ECC, resulting in incomplete and overcomplete cleansings. To address the PV effect, this work investigated an improved maximum a posteriori expectation-maximization (MAP-EM) image segmentation algorithm which simultaneously estimates tissue mixture percentages within each image voxel and statistical model parameters for the tissue distribution. Given the segmented tissue mixture information beyond the image voxel level, not only the PV effect has been satisfactorily addressed as a particular case of tissue mixture problem, but incomplete and overcomplete ECC causes could also be maximally avoided. For clinical application to CTC that involves several issues transferring from theoretical analysis to practical validation, an innovative initialization procedure and refined estimation strategy were proposed to build an ECC pipeline based on the MAP-EM segmentation. The pipeline was evaluated based on 52 patient CTC studies, downloaded from the website of the Virtual Colonoscopy Screening Resource Center, by two radiologists. A noticeable improvement over the authors' previous ECC pipeline was documented. Several typical cases were also presented to show visually the improved performance of the presented ECC pipeline.

UR - http://www.scopus.com/inward/record.url?scp=56749156908&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=56749156908&partnerID=8YFLogxK

U2 - 10.1118/1.3013591

DO - 10.1118/1.3013591

M3 - Article

VL - 35

SP - 5787

EP - 5798

JO - Medical Physics

JF - Medical Physics

SN - 0094-2405

IS - 12

ER -