L Shamir1, S M Ling, W Scott, M Hochberg, L Ferrucci, I G Goldberg. 1. Image Informatics and Computational Biology Unit, Laboratory of Genetics, NIA, NIH, 251 Bayview Boulevard, Baltimore, MD 21224, USA. shamirl@mail.nih.gov
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.
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.
Authors: I Boniatis; L Costaridou; D Cavouras; I Kalatzis; E Panagiotopoulos; G Panayiotakis Journal: Med Biol Eng Comput Date: 2006-08-15 Impact factor: 2.602
Authors: Nikita Orlov; Lior Shamir; Tomasz Macura; Josiah Johnston; D Mark Eckley; Ilya G Goldberg Journal: Pattern Recognit Lett Date: 2008-01 Impact factor: 3.756
Authors: Lior Shamir; Nikita Orlov; David Mark Eckley; Tomasz J Macura; Ilya G Goldberg Journal: Med Biol Eng Comput Date: 2008-07-31 Impact factor: 2.602
Authors: R I Bolbos; Jin Zuo; Suchandrima Banerjee; Thomas M Link; C Benjamin Ma; Xiaojuan Li; Sharmila Majumdar Journal: Osteoarthritis Cartilage Date: 2008-04-02 Impact factor: 6.576
Authors: Nikita V Orlov; Wayne W Chen; David Mark Eckley; Tomasz J Macura; Lior Shamir; Elaine S Jaffe; Ilya G Goldberg Journal: IEEE Trans Inf Technol Biomed Date: 2010-07
Authors: Nikita V Orlov; Ashani T Weeraratna; Stephen M Hewitt; Christopher E Coletta; John D Delaney; D Mark Eckley; Lior Shamir; Ilya G Goldberg Journal: Cytometry A Date: 2012-03-29 Impact factor: 4.355
Authors: B G Ashinsky; C E Coletta; M Bouhrara; V A Lukas; J M Boyle; D A Reiter; C P Neu; I G Goldberg; R G Spencer Journal: Osteoarthritis Cartilage Date: 2015-06-09 Impact factor: 6.576
Authors: Elliot Ensink; Jessica Sinha; Arkadeep Sinha; Huiyuan Tang; Heather M Calderone; Galen Hostetter; Jordan Winter; David Cherba; Randall E Brand; Peter J Allen; Lorenzo F Sempere; Brian B Haab Journal: Anal Chem Date: 2015-09-11 Impact factor: 6.986
Authors: Virginia Byers Kraus; Sheng Feng; ShengChu Wang; Scott White; Maureen Ainslie; Marie-Pierre Hellio Le Graverand; Alan Brett; Felix Eckstein; David J Hunter; Nancy E Lane; Mihra S Taljanovic; Thomas Schnitzer; H Cecil Charles Journal: Arthritis Rheum Date: 2013-07
Authors: Kevin A Thomas; Łukasz Kidziński; Eni Halilaj; Scott L Fleming; Guhan R Venkataraman; Edwin H G Oei; Garry E Gold; Scott L Delp Journal: Radiol Artif Intell Date: 2020-03-18