Early detection of radiographic knee osteoarthritis using computer-aided analysis

L. Shamir, S. M. Ling, W. Scott, M. Hochberg, L. Ferrucci, I. G. Goldberg

Research output: Contribution to journalArticle

Abstract

Objective: To determine whether computer-based analysis can detect features predictive of osteoarthritis (OA) development in radiographically normal knees. Method: A systematic computer-aided image analysis method weighted neighbor distances using a compound hierarchy of algorithms representing morphology (WND-CHARM) was used to analyze pairs of weight-bearing knee X-rays. Initial X-rays were all scored as normal Kellgren-Lawrence (KL) grade 0, and on follow-up approximately 20 years later either developed OA (defined as KL grade = 2) or remained normal. Results: The computer-aided method predicted whether a knee would change from KL grade 0 to grade 3 with 72% accuracy (P <0.00001), and to grade 2 with 62% accuracy (P <0.01). Although a large part of the predictive signal comes from the image tiles that contained the joint, the region adjacent to the tibial spines provided the strongest predictive signal. Conclusion: Radiographic features detectable using a computer-aided image analysis method can predict the future development of radiographic knee OA.

Original languageEnglish (US)
Pages (from-to)1307-1312
Number of pages6
JournalOsteoarthritis and Cartilage
Volume17
Issue number10
DOIs
StatePublished - Oct 2009
Externally publishedYes

Fingerprint

Computer aided analysis
Knee Osteoarthritis
Knee
Osteoarthritis
Image analysis
Bearings (structural)
X-Rays
X rays
Weight-Bearing
Tile
Spine
Joints

Keywords

  • Early detection
  • Image analysis
  • Osteoarthritis detection

ASJC Scopus subject areas

  • Biomedical Engineering
  • Orthopedics and Sports Medicine
  • Rheumatology

Cite this

Shamir, L., Ling, S. M., Scott, W., Hochberg, M., Ferrucci, L., & Goldberg, I. G. (2009). Early detection of radiographic knee osteoarthritis using computer-aided analysis. Osteoarthritis and Cartilage, 17(10), 1307-1312. https://doi.org/10.1016/j.joca.2009.04.010

Early detection of radiographic knee osteoarthritis using computer-aided analysis. / Shamir, L.; Ling, S. M.; Scott, W.; Hochberg, M.; Ferrucci, L.; Goldberg, I. G.

In: Osteoarthritis and Cartilage, Vol. 17, No. 10, 10.2009, p. 1307-1312.

Research output: Contribution to journalArticle

Shamir, L, Ling, SM, Scott, W, Hochberg, M, Ferrucci, L & Goldberg, IG 2009, 'Early detection of radiographic knee osteoarthritis using computer-aided analysis', Osteoarthritis and Cartilage, vol. 17, no. 10, pp. 1307-1312. https://doi.org/10.1016/j.joca.2009.04.010
Shamir, L. ; Ling, S. M. ; Scott, W. ; Hochberg, M. ; Ferrucci, L. ; Goldberg, I. G. / Early detection of radiographic knee osteoarthritis using computer-aided analysis. In: Osteoarthritis and Cartilage. 2009 ; Vol. 17, No. 10. pp. 1307-1312.
@article{f22090116f694eb89403fa061eaf9b94,
title = "Early detection of radiographic knee osteoarthritis using computer-aided analysis",
abstract = "Objective: To determine whether computer-based analysis can detect features predictive of osteoarthritis (OA) development in radiographically normal knees. Method: A systematic computer-aided image analysis method weighted neighbor distances using a compound hierarchy of algorithms representing morphology (WND-CHARM) was used to analyze pairs of weight-bearing knee X-rays. Initial X-rays were all scored as normal Kellgren-Lawrence (KL) grade 0, and on follow-up approximately 20 years later either developed OA (defined as KL grade = 2) or remained normal. Results: The computer-aided method predicted whether a knee would change from KL grade 0 to grade 3 with 72{\%} accuracy (P <0.00001), and to grade 2 with 62{\%} accuracy (P <0.01). Although a large part of the predictive signal comes from the image tiles that contained the joint, the region adjacent to the tibial spines provided the strongest predictive signal. Conclusion: Radiographic features detectable using a computer-aided image analysis method can predict the future development of radiographic knee OA.",
keywords = "Early detection, Image analysis, Osteoarthritis detection",
author = "L. Shamir and Ling, {S. M.} and W. Scott and M. Hochberg and L. Ferrucci and Goldberg, {I. G.}",
year = "2009",
month = "10",
doi = "10.1016/j.joca.2009.04.010",
language = "English (US)",
volume = "17",
pages = "1307--1312",
journal = "Osteoarthritis and Cartilage",
issn = "1063-4584",
publisher = "W.B. Saunders Ltd",
number = "10",

}

TY - JOUR

T1 - Early detection of radiographic knee osteoarthritis using computer-aided analysis

AU - Shamir, L.

AU - Ling, S. M.

AU - Scott, W.

AU - Hochberg, M.

AU - Ferrucci, L.

AU - Goldberg, I. G.

PY - 2009/10

Y1 - 2009/10

N2 - Objective: To determine whether computer-based analysis can detect features predictive of osteoarthritis (OA) development in radiographically normal knees. Method: A systematic computer-aided image analysis method weighted neighbor distances using a compound hierarchy of algorithms representing morphology (WND-CHARM) was used to analyze pairs of weight-bearing knee X-rays. Initial X-rays were all scored as normal Kellgren-Lawrence (KL) grade 0, and on follow-up approximately 20 years later either developed OA (defined as KL grade = 2) or remained normal. Results: The computer-aided method predicted whether a knee would change from KL grade 0 to grade 3 with 72% accuracy (P <0.00001), and to grade 2 with 62% accuracy (P <0.01). Although a large part of the predictive signal comes from the image tiles that contained the joint, the region adjacent to the tibial spines provided the strongest predictive signal. Conclusion: Radiographic features detectable using a computer-aided image analysis method can predict the future development of radiographic knee OA.

AB - Objective: To determine whether computer-based analysis can detect features predictive of osteoarthritis (OA) development in radiographically normal knees. Method: A systematic computer-aided image analysis method weighted neighbor distances using a compound hierarchy of algorithms representing morphology (WND-CHARM) was used to analyze pairs of weight-bearing knee X-rays. Initial X-rays were all scored as normal Kellgren-Lawrence (KL) grade 0, and on follow-up approximately 20 years later either developed OA (defined as KL grade = 2) or remained normal. Results: The computer-aided method predicted whether a knee would change from KL grade 0 to grade 3 with 72% accuracy (P <0.00001), and to grade 2 with 62% accuracy (P <0.01). Although a large part of the predictive signal comes from the image tiles that contained the joint, the region adjacent to the tibial spines provided the strongest predictive signal. Conclusion: Radiographic features detectable using a computer-aided image analysis method can predict the future development of radiographic knee OA.

KW - Early detection

KW - Image analysis

KW - Osteoarthritis detection

UR - http://www.scopus.com/inward/record.url?scp=70349246681&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70349246681&partnerID=8YFLogxK

U2 - 10.1016/j.joca.2009.04.010

DO - 10.1016/j.joca.2009.04.010

M3 - Article

C2 - 19426848

AN - SCOPUS:70349246681

VL - 17

SP - 1307

EP - 1312

JO - Osteoarthritis and Cartilage

JF - Osteoarthritis and Cartilage

SN - 1063-4584

IS - 10

ER -