Template-based level set segmentation using anatomical information

Application to quadriceps muscles in MR images from the osteoarthritis initiative

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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

We present a preliminary evaluation of an automated segmentation method of the quadriceps muscles from MR images of the thigh. The method is being developed to assist research into morphological properties of the quadriceps muscles as biomarkers of osteoarthritis (OA) incidence and progression. Our method uses an anatomically anchored, template-based initialization of the level set-based segmentation approach. A template image is selected using the Kullback-Leibler divergence measure based on the muscle and fat content of the thigh images. Contours of the quadriceps muscles of the chosen template are then semi-automatically registered to the image to be segmented using an affine transformation. These registered contours are used as initializations for the multi-phase level-set segmentation of the image, which is pre-processed to reduce arterial flow artifacts, the bias field, and intramuscular fat/connective tissue. Thirteen studies from eleven different subjects were analyzed. The performance was compared against manual segmentations using the Zijdenbos similarity index (ZSI). The ZSI means and standard deviations were: rectus femoris, 0.73 ± 0.13; vastus intermedius, 0.78 ± 0.09; vastus lateralis, 0.81 ± 0.14; vastus medialis, 0.85 ± 0.10.

Original languageEnglish (US)
Title of host publication2009 24th International Symposium on Computer and Information Sciences, ISCIS 2009
Pages24-28
Number of pages5
DOIs
StatePublished - Dec 1 2009
Externally publishedYes
Event2009 24th International Symposium on Computer and Information Sciences, ISCIS 2009 - Guzelyurt, Cyprus
Duration: Sep 14 2009Sep 16 2009

Other

Other2009 24th International Symposium on Computer and Information Sciences, ISCIS 2009
CountryCyprus
CityGuzelyurt
Period9/14/099/16/09

Fingerprint

Muscle
Oils and fats
Biomarkers
Tissue

Keywords

  • Level set
  • Osteoarthritis
  • Segmentation
  • Template

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Software

Cite this

Prescott, J. W., Swanson, M. S., Powell, K., Gurcan, M. N., Haq, F., Best, T., & Jackson, R. D. (2009). Template-based level set segmentation using anatomical information: Application to quadriceps muscles in MR images from the osteoarthritis initiative. In 2009 24th International Symposium on Computer and Information Sciences, ISCIS 2009 (pp. 24-28). [5291927] https://doi.org/10.1109/ISCIS.2009.5291927

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

2009 24th International Symposium on Computer and Information Sciences, ISCIS 2009. 2009. p. 24-28 5291927.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Prescott, JW, Swanson, MS, Powell, K, Gurcan, MN, Haq, F, Best, T & Jackson, RD 2009, Template-based level set segmentation using anatomical information: Application to quadriceps muscles in MR images from the osteoarthritis initiative. in 2009 24th International Symposium on Computer and Information Sciences, ISCIS 2009., 5291927, pp. 24-28, 2009 24th International Symposium on Computer and Information Sciences, ISCIS 2009, Guzelyurt, Cyprus, 9/14/09. https://doi.org/10.1109/ISCIS.2009.5291927
Prescott JW, Swanson MS, Powell K, Gurcan MN, Haq F, Best T et al. Template-based level set segmentation using anatomical information: Application to quadriceps muscles in MR images from the osteoarthritis initiative. In 2009 24th International Symposium on Computer and Information Sciences, ISCIS 2009. 2009. p. 24-28. 5291927 https://doi.org/10.1109/ISCIS.2009.5291927
Prescott, Jeffrey W. ; Swanson, Mark S. ; Powell, Kimerly ; Gurcan, Metin N. ; Haq, Furqan ; Best, Thomas ; Jackson, Rebecca D. / Template-based level set segmentation using anatomical information : Application to quadriceps muscles in MR images from the osteoarthritis initiative. 2009 24th International Symposium on Computer and Information Sciences, ISCIS 2009. 2009. pp. 24-28
@inproceedings{7c24f428de0745129a6bcc20fd8bbba3,
title = "Template-based level set segmentation using anatomical information: Application to quadriceps muscles in MR images from the osteoarthritis initiative",
abstract = "We present a preliminary evaluation of an automated segmentation method of the quadriceps muscles from MR images of the thigh. The method is being developed to assist research into morphological properties of the quadriceps muscles as biomarkers of osteoarthritis (OA) incidence and progression. Our method uses an anatomically anchored, template-based initialization of the level set-based segmentation approach. A template image is selected using the Kullback-Leibler divergence measure based on the muscle and fat content of the thigh images. Contours of the quadriceps muscles of the chosen template are then semi-automatically registered to the image to be segmented using an affine transformation. These registered contours are used as initializations for the multi-phase level-set segmentation of the image, which is pre-processed to reduce arterial flow artifacts, the bias field, and intramuscular fat/connective tissue. Thirteen studies from eleven different subjects were analyzed. The performance was compared against manual segmentations using the Zijdenbos similarity index (ZSI). The ZSI means and standard deviations were: rectus femoris, 0.73 ± 0.13; vastus intermedius, 0.78 ± 0.09; vastus lateralis, 0.81 ± 0.14; vastus medialis, 0.85 ± 0.10.",
keywords = "Level set, Osteoarthritis, Segmentation, Template",
author = "Prescott, {Jeffrey W.} and Swanson, {Mark S.} and Kimerly Powell and Gurcan, {Metin N.} and Furqan Haq and Thomas Best and Jackson, {Rebecca D.}",
year = "2009",
month = "12",
day = "1",
doi = "10.1109/ISCIS.2009.5291927",
language = "English (US)",
isbn = "9781424450237",
pages = "24--28",
booktitle = "2009 24th International Symposium on Computer and Information Sciences, ISCIS 2009",

}

TY - GEN

T1 - Template-based level set segmentation using anatomical information

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

AU - Prescott, Jeffrey W.

AU - Swanson, Mark S.

AU - Powell, Kimerly

AU - Gurcan, Metin N.

AU - Haq, Furqan

AU - Best, Thomas

AU - Jackson, Rebecca D.

PY - 2009/12/1

Y1 - 2009/12/1

N2 - We present a preliminary evaluation of an automated segmentation method of the quadriceps muscles from MR images of the thigh. The method is being developed to assist research into morphological properties of the quadriceps muscles as biomarkers of osteoarthritis (OA) incidence and progression. Our method uses an anatomically anchored, template-based initialization of the level set-based segmentation approach. A template image is selected using the Kullback-Leibler divergence measure based on the muscle and fat content of the thigh images. Contours of the quadriceps muscles of the chosen template are then semi-automatically registered to the image to be segmented using an affine transformation. These registered contours are used as initializations for the multi-phase level-set segmentation of the image, which is pre-processed to reduce arterial flow artifacts, the bias field, and intramuscular fat/connective tissue. Thirteen studies from eleven different subjects were analyzed. The performance was compared against manual segmentations using the Zijdenbos similarity index (ZSI). The ZSI means and standard deviations were: rectus femoris, 0.73 ± 0.13; vastus intermedius, 0.78 ± 0.09; vastus lateralis, 0.81 ± 0.14; vastus medialis, 0.85 ± 0.10.

AB - We present a preliminary evaluation of an automated segmentation method of the quadriceps muscles from MR images of the thigh. The method is being developed to assist research into morphological properties of the quadriceps muscles as biomarkers of osteoarthritis (OA) incidence and progression. Our method uses an anatomically anchored, template-based initialization of the level set-based segmentation approach. A template image is selected using the Kullback-Leibler divergence measure based on the muscle and fat content of the thigh images. Contours of the quadriceps muscles of the chosen template are then semi-automatically registered to the image to be segmented using an affine transformation. These registered contours are used as initializations for the multi-phase level-set segmentation of the image, which is pre-processed to reduce arterial flow artifacts, the bias field, and intramuscular fat/connective tissue. Thirteen studies from eleven different subjects were analyzed. The performance was compared against manual segmentations using the Zijdenbos similarity index (ZSI). The ZSI means and standard deviations were: rectus femoris, 0.73 ± 0.13; vastus intermedius, 0.78 ± 0.09; vastus lateralis, 0.81 ± 0.14; vastus medialis, 0.85 ± 0.10.

KW - Level set

KW - Osteoarthritis

KW - Segmentation

KW - Template

UR - http://www.scopus.com/inward/record.url?scp=73949132016&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=73949132016&partnerID=8YFLogxK

U2 - 10.1109/ISCIS.2009.5291927

DO - 10.1109/ISCIS.2009.5291927

M3 - Conference contribution

SN - 9781424450237

SP - 24

EP - 28

BT - 2009 24th International Symposium on Computer and Information Sciences, ISCIS 2009

ER -