Comparison of two-dimensional and three-dimensional iterative watershed segmentation methods in hepatic tumor volumetrics

Shonket Ray, Rosalie J Hagge, Marijo Gillen, Miguel Cerejo, Shidrokh Shakeri, Laurel A Beckett, Tamara Greasby, Ramsey D Badawi

Research output: Contribution to journalArticle

23 Citations (Scopus)

Abstract

In this work the authors compare the accuracy of two-dimensional (2D) and three-dimensional (3D) implementations of a computer-aided image segmentation method to that of physician observers (using manual outlining) for volume measurements of liver tumors visualized with diagnostic contrast-enhanced and PET/CT-based non-contrast-enhanced (PET-CT) CT scans. The method assessed is a hybridization of the watershed method using observer-set markers with a gradient vector flow approach. This method is known as the iterative watershed segmentation (IWS) method. Initial assessments are performed using software phantoms that model a range of tumor shapes, noise levels, and noise qualities. IWS is then applied to CT image sets of patients with identified hepatic tumors and compared to the physicians' manual outlines on the same tumors. The repeatability of the physicians' measurements is also assessed. IWS utilizes multiple levels of segmentation performed with the use of "fuzzy regions" that could be considered part of a selected tumor. In phantom studies, the outermost volume outline for level 1 (called level 1_1 consisting of inner region plus fuzzy region) was generally the most accurate. For in vivo studies, the level 1_1 and the second outermost outline for level 2 (called level 2_2 consisting of inner region plus two fuzzy regions) typically had the smallest percent error values when compared to physician observer volume estimates. Our data indicate that allowing the operator to choose the "best result" level iteration outline from all generated outlines would likely give the more accurate volume for a given tumor rather than automatically choosing a particular level iteration outline. The preliminary in vivo results indicate that 2D-IWS is likely to be more accurate than 3D-IWS in relation to the observer volume estimates.

Original languageEnglish (US)
Pages (from-to)5869-5881
Number of pages13
JournalMedical Physics
Volume35
Issue number12
DOIs
StatePublished - 2008

Fingerprint

Liver
Physicians
Neoplasms
Noise
Software

Keywords

  • Active contours
  • Gradient vector flow
  • Iterative watershed method
  • Marker-based watershed
  • RECIST
  • Tumor segmentation

ASJC Scopus subject areas

  • Biophysics
  • Radiology Nuclear Medicine and imaging

Cite this

Comparison of two-dimensional and three-dimensional iterative watershed segmentation methods in hepatic tumor volumetrics. / Ray, Shonket; Hagge, Rosalie J; Gillen, Marijo; Cerejo, Miguel; Shakeri, Shidrokh; Beckett, Laurel A; Greasby, Tamara; Badawi, Ramsey D.

In: Medical Physics, Vol. 35, No. 12, 2008, p. 5869-5881.

Research output: Contribution to journalArticle

Ray, Shonket ; Hagge, Rosalie J ; Gillen, Marijo ; Cerejo, Miguel ; Shakeri, Shidrokh ; Beckett, Laurel A ; Greasby, Tamara ; Badawi, Ramsey D. / Comparison of two-dimensional and three-dimensional iterative watershed segmentation methods in hepatic tumor volumetrics. In: Medical Physics. 2008 ; Vol. 35, No. 12. pp. 5869-5881.
@article{4e73b7a254424cbe829e6190faf835e3,
title = "Comparison of two-dimensional and three-dimensional iterative watershed segmentation methods in hepatic tumor volumetrics",
abstract = "In this work the authors compare the accuracy of two-dimensional (2D) and three-dimensional (3D) implementations of a computer-aided image segmentation method to that of physician observers (using manual outlining) for volume measurements of liver tumors visualized with diagnostic contrast-enhanced and PET/CT-based non-contrast-enhanced (PET-CT) CT scans. The method assessed is a hybridization of the watershed method using observer-set markers with a gradient vector flow approach. This method is known as the iterative watershed segmentation (IWS) method. Initial assessments are performed using software phantoms that model a range of tumor shapes, noise levels, and noise qualities. IWS is then applied to CT image sets of patients with identified hepatic tumors and compared to the physicians' manual outlines on the same tumors. The repeatability of the physicians' measurements is also assessed. IWS utilizes multiple levels of segmentation performed with the use of {"}fuzzy regions{"} that could be considered part of a selected tumor. In phantom studies, the outermost volume outline for level 1 (called level 1_1 consisting of inner region plus fuzzy region) was generally the most accurate. For in vivo studies, the level 1_1 and the second outermost outline for level 2 (called level 2_2 consisting of inner region plus two fuzzy regions) typically had the smallest percent error values when compared to physician observer volume estimates. Our data indicate that allowing the operator to choose the {"}best result{"} level iteration outline from all generated outlines would likely give the more accurate volume for a given tumor rather than automatically choosing a particular level iteration outline. The preliminary in vivo results indicate that 2D-IWS is likely to be more accurate than 3D-IWS in relation to the observer volume estimates.",
keywords = "Active contours, Gradient vector flow, Iterative watershed method, Marker-based watershed, RECIST, Tumor segmentation",
author = "Shonket Ray and Hagge, {Rosalie J} and Marijo Gillen and Miguel Cerejo and Shidrokh Shakeri and Beckett, {Laurel A} and Tamara Greasby and Badawi, {Ramsey D}",
year = "2008",
doi = "10.1118/1.3013561",
language = "English (US)",
volume = "35",
pages = "5869--5881",
journal = "Medical Physics",
issn = "0094-2405",
publisher = "AAPM - American Association of Physicists in Medicine",
number = "12",

}

TY - JOUR

T1 - Comparison of two-dimensional and three-dimensional iterative watershed segmentation methods in hepatic tumor volumetrics

AU - Ray, Shonket

AU - Hagge, Rosalie J

AU - Gillen, Marijo

AU - Cerejo, Miguel

AU - Shakeri, Shidrokh

AU - Beckett, Laurel A

AU - Greasby, Tamara

AU - Badawi, Ramsey D

PY - 2008

Y1 - 2008

N2 - In this work the authors compare the accuracy of two-dimensional (2D) and three-dimensional (3D) implementations of a computer-aided image segmentation method to that of physician observers (using manual outlining) for volume measurements of liver tumors visualized with diagnostic contrast-enhanced and PET/CT-based non-contrast-enhanced (PET-CT) CT scans. The method assessed is a hybridization of the watershed method using observer-set markers with a gradient vector flow approach. This method is known as the iterative watershed segmentation (IWS) method. Initial assessments are performed using software phantoms that model a range of tumor shapes, noise levels, and noise qualities. IWS is then applied to CT image sets of patients with identified hepatic tumors and compared to the physicians' manual outlines on the same tumors. The repeatability of the physicians' measurements is also assessed. IWS utilizes multiple levels of segmentation performed with the use of "fuzzy regions" that could be considered part of a selected tumor. In phantom studies, the outermost volume outline for level 1 (called level 1_1 consisting of inner region plus fuzzy region) was generally the most accurate. For in vivo studies, the level 1_1 and the second outermost outline for level 2 (called level 2_2 consisting of inner region plus two fuzzy regions) typically had the smallest percent error values when compared to physician observer volume estimates. Our data indicate that allowing the operator to choose the "best result" level iteration outline from all generated outlines would likely give the more accurate volume for a given tumor rather than automatically choosing a particular level iteration outline. The preliminary in vivo results indicate that 2D-IWS is likely to be more accurate than 3D-IWS in relation to the observer volume estimates.

AB - In this work the authors compare the accuracy of two-dimensional (2D) and three-dimensional (3D) implementations of a computer-aided image segmentation method to that of physician observers (using manual outlining) for volume measurements of liver tumors visualized with diagnostic contrast-enhanced and PET/CT-based non-contrast-enhanced (PET-CT) CT scans. The method assessed is a hybridization of the watershed method using observer-set markers with a gradient vector flow approach. This method is known as the iterative watershed segmentation (IWS) method. Initial assessments are performed using software phantoms that model a range of tumor shapes, noise levels, and noise qualities. IWS is then applied to CT image sets of patients with identified hepatic tumors and compared to the physicians' manual outlines on the same tumors. The repeatability of the physicians' measurements is also assessed. IWS utilizes multiple levels of segmentation performed with the use of "fuzzy regions" that could be considered part of a selected tumor. In phantom studies, the outermost volume outline for level 1 (called level 1_1 consisting of inner region plus fuzzy region) was generally the most accurate. For in vivo studies, the level 1_1 and the second outermost outline for level 2 (called level 2_2 consisting of inner region plus two fuzzy regions) typically had the smallest percent error values when compared to physician observer volume estimates. Our data indicate that allowing the operator to choose the "best result" level iteration outline from all generated outlines would likely give the more accurate volume for a given tumor rather than automatically choosing a particular level iteration outline. The preliminary in vivo results indicate that 2D-IWS is likely to be more accurate than 3D-IWS in relation to the observer volume estimates.

KW - Active contours

KW - Gradient vector flow

KW - Iterative watershed method

KW - Marker-based watershed

KW - RECIST

KW - Tumor segmentation

UR - http://www.scopus.com/inward/record.url?scp=56749104626&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=56749104626&partnerID=8YFLogxK

U2 - 10.1118/1.3013561

DO - 10.1118/1.3013561

M3 - Article

VL - 35

SP - 5869

EP - 5881

JO - Medical Physics

JF - Medical Physics

SN - 0094-2405

IS - 12

ER -