« Previous Next »Osteoarthritis and Cartilage
Volume 17, Issue 10 , Pages 1307-1312, October 2009

Early detection of radiographic knee osteoarthritis using computer-aided analysis

L. Shamir
- Image Informatics and Computational Biology Unit, Laboratory of Genetics, NIA, NIH, 251 Bayview Boulevard, Baltimore, MD 21224, USA
- Address correspondence and reprint requests to: L. Shamir, Image Informatics and Computational Biology Unit, Laboratory of Genetics, NIA, NIH, 251 Bayview Boulevard, Baltimore, MD 21224, USA. Tel: 1-410-558-8682; Fax: 1-410-558-8331.
S.M. Ling
- Clinical Research Branch, NIA, NIH, 3001 Hanover Street, MD 21225, USA
W. Scott
- Department of Radiology, Johns Hopkins School of Medicine, 600 North Wolfe Street, Baltimore, MD 21287, USA
M. Hochberg
- Department of Medicine, University of Maryland Medical Center, 22 S. Greene Street, Baltimore, MD 21201, USA
L. Ferrucci
- Clinical Research Branch, NIA, NIH, 3001 Hanover Street, MD 21225, USA
I.G. Goldberg
- Image Informatics and Computational Biology Unit, Laboratory of Genetics, NIA, NIH, 251 Bayview Boulevard, Baltimore, MD 21224, USA

Received 8 December 2008; accepted 12 April 2009. published online 18 May 2009.

Summary

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.