Anatomically anchored template-based level set segmentation

Application to quadriceps muscles in MR images from the osteoarthritis initiative

Jeffrey W. Prescott, Thomas Best, Mark S. Swanson, Furqan Haq, Rebecca D. Jackson, Metin N. Gurcan

Research output: Contribution to journalArticle

22 Citations (Scopus)

Abstract

In this paper, we present a semi-automated segmentation method for magnetic resonance images of the quadriceps muscles. Our method uses an anatomically anchored, template-based initialization of the level set-based segmentation approach. The method only requires the input of a single point from the user inside the rectus femoris. The templates are quantitatively selected from a set of images based on modes in the patient population, namely, sex and body type. For a given image to be segmented, a template is selected based on the smallest Kullback-Leibler divergence between the histograms of that image and the set of templates. The chosen template is then employed as an initialization for a level set segmentation, which captures individual anatomical variations in the image to be segmented. Images from 103 subjects were analyzed using the developed method. The algorithm was trained on a randomly selected subset of 50 subjects (25 men and 25 women) and tested on the remaining 53 subjects. The performance of the algorithm on the test set was compared against the ground truth using the Zijdenbos similarity index (ZSI). The average ZSI means and standard deviations against two different manual readers were as follows: rectus femoris, 0.78±0.12; vastus intermedius, 0.79±0.10; vastus lateralis, 0.82±0.08; and vastus medialis, 0.69±0.16.

Original languageEnglish (US)
Pages (from-to)28-43
Number of pages16
JournalJournal of Digital Imaging
Volume24
Issue number1
DOIs
StatePublished - Feb 1 2011
Externally publishedYes

Fingerprint

Quadriceps Muscle
Osteoarthritis
Muscle
Magnetic resonance
Set theory
Somatotypes
Magnetic Resonance Spectroscopy
Population

Keywords

  • level sets
  • MRI
  • muscle segmentation
  • Osteoarthritis
  • templates

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging
  • Radiological and Ultrasound Technology
  • Computer Science Applications
  • Medicine(all)

Cite this

Anatomically anchored template-based level set segmentation : Application to quadriceps muscles in MR images from the osteoarthritis initiative. / Prescott, Jeffrey W.; Best, Thomas; Swanson, Mark S.; Haq, Furqan; Jackson, Rebecca D.; Gurcan, Metin N.

In: Journal of Digital Imaging, Vol. 24, No. 1, 01.02.2011, p. 28-43.

Research output: Contribution to journalArticle

Prescott, Jeffrey W. ; Best, Thomas ; Swanson, Mark S. ; Haq, Furqan ; Jackson, Rebecca D. ; Gurcan, Metin N. / Anatomically anchored template-based level set segmentation : Application to quadriceps muscles in MR images from the osteoarthritis initiative. In: Journal of Digital Imaging. 2011 ; Vol. 24, No. 1. pp. 28-43.
@article{9b10c1e3ee5c4a81814c6e9ef98a3459,
title = "Anatomically anchored template-based level set segmentation: Application to quadriceps muscles in MR images from the osteoarthritis initiative",
abstract = "In this paper, we present a semi-automated segmentation method for magnetic resonance images of the quadriceps muscles. Our method uses an anatomically anchored, template-based initialization of the level set-based segmentation approach. The method only requires the input of a single point from the user inside the rectus femoris. The templates are quantitatively selected from a set of images based on modes in the patient population, namely, sex and body type. For a given image to be segmented, a template is selected based on the smallest Kullback-Leibler divergence between the histograms of that image and the set of templates. The chosen template is then employed as an initialization for a level set segmentation, which captures individual anatomical variations in the image to be segmented. Images from 103 subjects were analyzed using the developed method. The algorithm was trained on a randomly selected subset of 50 subjects (25 men and 25 women) and tested on the remaining 53 subjects. The performance of the algorithm on the test set was compared against the ground truth using the Zijdenbos similarity index (ZSI). The average ZSI means and standard deviations against two different manual readers were as follows: rectus femoris, 0.78±0.12; vastus intermedius, 0.79±0.10; vastus lateralis, 0.82±0.08; and vastus medialis, 0.69±0.16.",
keywords = "level sets, MRI, muscle segmentation, Osteoarthritis, templates",
author = "Prescott, {Jeffrey W.} and Thomas Best and Swanson, {Mark S.} and Furqan Haq and Jackson, {Rebecca D.} and Gurcan, {Metin N.}",
year = "2011",
month = "2",
day = "1",
doi = "10.1007/s10278-009-9260-2",
language = "English (US)",
volume = "24",
pages = "28--43",
journal = "Journal of Digital Imaging",
issn = "0897-1889",
publisher = "Springer New York",
number = "1",

}

TY - JOUR

T1 - Anatomically anchored template-based level set segmentation

T2 - Application to quadriceps muscles in MR images from the osteoarthritis initiative

AU - Prescott, Jeffrey W.

AU - Best, Thomas

AU - Swanson, Mark S.

AU - Haq, Furqan

AU - Jackson, Rebecca D.

AU - Gurcan, Metin N.

PY - 2011/2/1

Y1 - 2011/2/1

N2 - In this paper, we present a semi-automated segmentation method for magnetic resonance images of the quadriceps muscles. Our method uses an anatomically anchored, template-based initialization of the level set-based segmentation approach. The method only requires the input of a single point from the user inside the rectus femoris. The templates are quantitatively selected from a set of images based on modes in the patient population, namely, sex and body type. For a given image to be segmented, a template is selected based on the smallest Kullback-Leibler divergence between the histograms of that image and the set of templates. The chosen template is then employed as an initialization for a level set segmentation, which captures individual anatomical variations in the image to be segmented. Images from 103 subjects were analyzed using the developed method. The algorithm was trained on a randomly selected subset of 50 subjects (25 men and 25 women) and tested on the remaining 53 subjects. The performance of the algorithm on the test set was compared against the ground truth using the Zijdenbos similarity index (ZSI). The average ZSI means and standard deviations against two different manual readers were as follows: rectus femoris, 0.78±0.12; vastus intermedius, 0.79±0.10; vastus lateralis, 0.82±0.08; and vastus medialis, 0.69±0.16.

AB - In this paper, we present a semi-automated segmentation method for magnetic resonance images of the quadriceps muscles. Our method uses an anatomically anchored, template-based initialization of the level set-based segmentation approach. The method only requires the input of a single point from the user inside the rectus femoris. The templates are quantitatively selected from a set of images based on modes in the patient population, namely, sex and body type. For a given image to be segmented, a template is selected based on the smallest Kullback-Leibler divergence between the histograms of that image and the set of templates. The chosen template is then employed as an initialization for a level set segmentation, which captures individual anatomical variations in the image to be segmented. Images from 103 subjects were analyzed using the developed method. The algorithm was trained on a randomly selected subset of 50 subjects (25 men and 25 women) and tested on the remaining 53 subjects. The performance of the algorithm on the test set was compared against the ground truth using the Zijdenbos similarity index (ZSI). The average ZSI means and standard deviations against two different manual readers were as follows: rectus femoris, 0.78±0.12; vastus intermedius, 0.79±0.10; vastus lateralis, 0.82±0.08; and vastus medialis, 0.69±0.16.

KW - level sets

KW - MRI

KW - muscle segmentation

KW - Osteoarthritis

KW - templates

UR - http://www.scopus.com/inward/record.url?scp=79751534616&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79751534616&partnerID=8YFLogxK

U2 - 10.1007/s10278-009-9260-2

DO - 10.1007/s10278-009-9260-2

M3 - Article

VL - 24

SP - 28

EP - 43

JO - Journal of Digital Imaging

JF - Journal of Digital Imaging

SN - 0897-1889

IS - 1

ER -