Semi-automated segmentation to assess the lateral meniscus in normal and osteoarthritic knees

M. S. Swanson, J. W. Prescott, Thomas Best, K. Powell, R. D. Jackson, F. Haq, M. N. Gurcan

Research output: Contribution to journalArticle

31 Citations (Scopus)

Abstract

Objective: The goal of this study was to develop an algorithm to semi-automatically segment the meniscus in a series of magnetic resonance (MR) images to use for normal knees and those with moderate osteoarthritis (OA). Method: The segmentation method was developed then evaluated on 10 baseline MR images obtained from subjects with no evidence, symptoms, or risk factors of knee (OA), and 14 from subjects with established knee OA enrolled in the Osteoarthritis Initiative (OAI). After manually choosing a seed point within the meniscus, a threshold level was calculated through a Gaussian fit model. Under anatomical, intensity, and range constraints, a threshold operation was completed followed by conditional dilation and post-processing. The post-processing operation reevaluates the pixels included and excluded in the area surrounding the meniscus to improve accuracy. The developed method was evaluated for both normal and degenerative menisci by comparing the segmentation algorithm results with manual segmentations from five human readers. Results: The semi-automated segmentation method produces results similar to those of trained observers, with an average similarity index over 0.80 for normal participants and 0.75, 0.67, and 0.64 for participants with established knee OA with Osteoarthritis Research Society International (OARSI) joint space narrowing (JSN) scores of 0, one, and two respectively. Conclusion: The semi-automatic segmentation method produced accurate and consistent segmentations of the meniscus when compared to manual segmentations in the assessment of normal menisci in mild to moderate OA. Future studies will examine the change in volume, thickness, and intensity characteristics at different stages of OA.

Original languageEnglish (US)
Pages (from-to)344-353
Number of pages10
JournalOsteoarthritis and Cartilage
Volume18
Issue number3
DOIs
StatePublished - Mar 1 2010
Externally publishedYes

Fingerprint

Tibial Meniscus
Magnetic resonance
Knee
Osteoarthritis
Knee Osteoarthritis
Processing
Seed
Pixels
Magnetic Resonance Spectroscopy
Meniscus
Dilatation
Seeds
Joints

Keywords

  • Magnetic resonance imaging
  • Meniscus
  • Osteoarthritis
  • Segmentation

ASJC Scopus subject areas

  • Biomedical Engineering
  • Orthopedics and Sports Medicine
  • Rheumatology

Cite this

Semi-automated segmentation to assess the lateral meniscus in normal and osteoarthritic knees. / Swanson, M. S.; Prescott, J. W.; Best, Thomas; Powell, K.; Jackson, R. D.; Haq, F.; Gurcan, M. N.

In: Osteoarthritis and Cartilage, Vol. 18, No. 3, 01.03.2010, p. 344-353.

Research output: Contribution to journalArticle

Swanson, M. S. ; Prescott, J. W. ; Best, Thomas ; Powell, K. ; Jackson, R. D. ; Haq, F. ; Gurcan, M. N. / Semi-automated segmentation to assess the lateral meniscus in normal and osteoarthritic knees. In: Osteoarthritis and Cartilage. 2010 ; Vol. 18, No. 3. pp. 344-353.
@article{f61d0843869f4667936dc509d8114e32,
title = "Semi-automated segmentation to assess the lateral meniscus in normal and osteoarthritic knees",
abstract = "Objective: The goal of this study was to develop an algorithm to semi-automatically segment the meniscus in a series of magnetic resonance (MR) images to use for normal knees and those with moderate osteoarthritis (OA). Method: The segmentation method was developed then evaluated on 10 baseline MR images obtained from subjects with no evidence, symptoms, or risk factors of knee (OA), and 14 from subjects with established knee OA enrolled in the Osteoarthritis Initiative (OAI). After manually choosing a seed point within the meniscus, a threshold level was calculated through a Gaussian fit model. Under anatomical, intensity, and range constraints, a threshold operation was completed followed by conditional dilation and post-processing. The post-processing operation reevaluates the pixels included and excluded in the area surrounding the meniscus to improve accuracy. The developed method was evaluated for both normal and degenerative menisci by comparing the segmentation algorithm results with manual segmentations from five human readers. Results: The semi-automated segmentation method produces results similar to those of trained observers, with an average similarity index over 0.80 for normal participants and 0.75, 0.67, and 0.64 for participants with established knee OA with Osteoarthritis Research Society International (OARSI) joint space narrowing (JSN) scores of 0, one, and two respectively. Conclusion: The semi-automatic segmentation method produced accurate and consistent segmentations of the meniscus when compared to manual segmentations in the assessment of normal menisci in mild to moderate OA. Future studies will examine the change in volume, thickness, and intensity characteristics at different stages of OA.",
keywords = "Magnetic resonance imaging, Meniscus, Osteoarthritis, Segmentation",
author = "Swanson, {M. S.} and Prescott, {J. W.} and Thomas Best and K. Powell and Jackson, {R. D.} and F. Haq and Gurcan, {M. N.}",
year = "2010",
month = "3",
day = "1",
doi = "10.1016/j.joca.2009.10.004",
language = "English (US)",
volume = "18",
pages = "344--353",
journal = "Osteoarthritis and Cartilage",
issn = "1063-4584",
publisher = "W.B. Saunders Ltd",
number = "3",

}

TY - JOUR

T1 - Semi-automated segmentation to assess the lateral meniscus in normal and osteoarthritic knees

AU - Swanson, M. S.

AU - Prescott, J. W.

AU - Best, Thomas

AU - Powell, K.

AU - Jackson, R. D.

AU - Haq, F.

AU - Gurcan, M. N.

PY - 2010/3/1

Y1 - 2010/3/1

N2 - Objective: The goal of this study was to develop an algorithm to semi-automatically segment the meniscus in a series of magnetic resonance (MR) images to use for normal knees and those with moderate osteoarthritis (OA). Method: The segmentation method was developed then evaluated on 10 baseline MR images obtained from subjects with no evidence, symptoms, or risk factors of knee (OA), and 14 from subjects with established knee OA enrolled in the Osteoarthritis Initiative (OAI). After manually choosing a seed point within the meniscus, a threshold level was calculated through a Gaussian fit model. Under anatomical, intensity, and range constraints, a threshold operation was completed followed by conditional dilation and post-processing. The post-processing operation reevaluates the pixels included and excluded in the area surrounding the meniscus to improve accuracy. The developed method was evaluated for both normal and degenerative menisci by comparing the segmentation algorithm results with manual segmentations from five human readers. Results: The semi-automated segmentation method produces results similar to those of trained observers, with an average similarity index over 0.80 for normal participants and 0.75, 0.67, and 0.64 for participants with established knee OA with Osteoarthritis Research Society International (OARSI) joint space narrowing (JSN) scores of 0, one, and two respectively. Conclusion: The semi-automatic segmentation method produced accurate and consistent segmentations of the meniscus when compared to manual segmentations in the assessment of normal menisci in mild to moderate OA. Future studies will examine the change in volume, thickness, and intensity characteristics at different stages of OA.

AB - Objective: The goal of this study was to develop an algorithm to semi-automatically segment the meniscus in a series of magnetic resonance (MR) images to use for normal knees and those with moderate osteoarthritis (OA). Method: The segmentation method was developed then evaluated on 10 baseline MR images obtained from subjects with no evidence, symptoms, or risk factors of knee (OA), and 14 from subjects with established knee OA enrolled in the Osteoarthritis Initiative (OAI). After manually choosing a seed point within the meniscus, a threshold level was calculated through a Gaussian fit model. Under anatomical, intensity, and range constraints, a threshold operation was completed followed by conditional dilation and post-processing. The post-processing operation reevaluates the pixels included and excluded in the area surrounding the meniscus to improve accuracy. The developed method was evaluated for both normal and degenerative menisci by comparing the segmentation algorithm results with manual segmentations from five human readers. Results: The semi-automated segmentation method produces results similar to those of trained observers, with an average similarity index over 0.80 for normal participants and 0.75, 0.67, and 0.64 for participants with established knee OA with Osteoarthritis Research Society International (OARSI) joint space narrowing (JSN) scores of 0, one, and two respectively. Conclusion: The semi-automatic segmentation method produced accurate and consistent segmentations of the meniscus when compared to manual segmentations in the assessment of normal menisci in mild to moderate OA. Future studies will examine the change in volume, thickness, and intensity characteristics at different stages of OA.

KW - Magnetic resonance imaging

KW - Meniscus

KW - Osteoarthritis

KW - Segmentation

UR - http://www.scopus.com/inward/record.url?scp=76549126338&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=76549126338&partnerID=8YFLogxK

U2 - 10.1016/j.joca.2009.10.004

DO - 10.1016/j.joca.2009.10.004

M3 - Article

VL - 18

SP - 344

EP - 353

JO - Osteoarthritis and Cartilage

JF - Osteoarthritis and Cartilage

SN - 1063-4584

IS - 3

ER -