Predicting early symptomatic osteoarthritis in the human knee using machine learning classification of magnetic resonance images from the osteoarthritis initiative

Journal of Orthopaedic Research

Volumn 35, Issue 10, 2017, Pages 2243-2250

  Ashinsky, Beth G ^a   Bouhrara, Mustapha ^a   Coletta, Christopher E ^a   Lehallier, Benoit ^b   Urish, Kenneth L ^c   Lin, Ping Chang ^d   Goldberg, Ilya G ^a   Spencer, Richard G ^a  

^a NATIONAL INSTITUTE ON AGING   (United States)

^b STANFORD UNIVERSITY SCHOOL OF MEDICINE   (United States)

^c UNIVERSITY OF PITTSBURGH   (United States)

^d HOWARD UNIVERSITY COLLEGE OF MEDICINE   (United States)

Author keywords

classification; MRI; osteoarthritis; pattern recognition; registration; segmentation

Indexed keywords

ADULT; ARTICLE; ARTICULAR CARTILAGE; CASE CONTROL STUDY; CLINICAL EVALUATION; COHORT ANALYSIS; CONTROLLED STUDY; DIAGNOSTIC ACCURACY; DIAGNOSTIC TEST ACCURACY STUDY; FEMORAL CONDYLE; HUMAN; IMAGE ANALYSIS; INCIDENCE; KNEE; KNEE OSTEOARTHRITIS; KNEE RADIOGRAPHY; LEARNING ALGORITHM; MACHINE LEARNING; MAJOR CLINICAL STUDY; MIDDLE AGED; NUCLEAR MAGNETIC RESONANCE IMAGING; NUCLEAR MAGNETIC RESONANCE SCANNER; PRIORITY JOURNAL; REGISTRATION; SENSITIVITY AND SPECIFICITY; SYMPTOM; WEIGHT BEARING; WESTERN ONTARIO AND MCMASTER UNIVERSITIES OSTEOARTHRITIS INDEX; WND CHRM ALGORITHM; ALGORITHM; DIAGNOSTIC IMAGING; REGRESSION ANALYSIS;

ALGORITHMS; CARTILAGE, ARTICULAR; COHORT STUDIES; HUMANS; MACHINE LEARNING; MAGNETIC RESONANCE IMAGING; MIDDLE AGED; OSTEOARTHRITIS, KNEE; REGRESSION ANALYSIS;

EID: 85016411648     PISSN: 07360266     EISSN: 1554527X     Source Type: Journal    
DOI: 10.1002/jor.23519     Document Type: Article

References (45)

1. Swedberg JA, Steinbauer JR. 1992. Osteoarthritis. Am Fam Physician 45:557–568.
2. Davis MA. 1988. Epidemiology of osteoarthritis. Clin Geriatr Med 4:241–255.
3. Braun HJ, Gold GE. 2011. Advanced MRI of articular cartilage. Imaging Med 3:541–555.
4. Braun HJ, Gold GE. 2012. Diagnosis of osteoarthritis: imaging. Bone 51:278–288.
5. Ashinsky B, Bouhrara M, Urish KL, et al. 2015. Predicting early osteoarthritis in the human knee: pattern recognition and machine learning classification of magnetic resonance images. Las Vegas, NV: The Orthopaedic Research Society.
6. Urish KL, Keffalas MG, Durkin JR, et al. 2013. T2 texture index of cartilage can predict early symptomatic OA progression: data from the osteoarthritis initiative. Osteoarthritis Cartilage 21:1550–1557.
7. Kauffmann C, Gravel P, Godbout B, et al. 2003. Computer-aided method for quantification of cartilage thickness and volume changes using MRI: validation study using a synthetic model. IEEE Trans Biomed Eng 50:978–988.
8. Ashinsky BG, Coletta CE, Bouhrara MB, et al. 2015. Machine learning classification of OARSI-scored human articular cartilage using magnetic resonance imaging. Osteoarthritis Cartilage 10:1704–1712.
9. Shamir L, Orlov N, Eckley DM, et al. 2008. Wndchrm—an open source utility for biological image analysis. Source Code Biol Med 3:13.
10. Pritzker KP, Gay S, Jimenez SA, et al. 2006. Osteoarthritis cartilage histopathology: grading and staging. Osteoarthritis Cartilage 14:13–29.
11. Peterfy CG, Schneider E, Nevitt M. 2008. The osteoarthritis initiative: report on the design rationale for the magnetic resonance imaging protocol for the knee. Osteoarthritis Cartilage 16:1433–1441.
12. Bellamy N, Buchanan WW, Goldsmith CH, et al. 1988. Validation study of WOMAC: a health status instrument for measuring clinically important patient relevant outcomes to antirheumatic drug therapy in patients with osteoarthritis of the hip or knee. J Rheumatol 15:1833–1840.
13. Folkesson J, Dam EB, Olsen OF, et al. 2007. Segmenting articular cartilage automatically using a voxel classification approach. IEEE Trans Med Imaging 26:106–115.
14. Fripp J, Crozier S, Warfield SK, et al. 2010. Automatic segmentation and quantitative analysis of the articular cartilages from magnetic resonance images of the knee. IEEE Trans Med Imaging 29:55–64.
15. Glocker B, Komodakis N, Paragios N, et al. 2007. Primal/dual linear programming and statistical atlases for cartilage segmentation. Med Image Comput Comput Assist Interv 10:536–543.
16. Schneider E, Nevitt M, McCulloch C, et al. 2012. Equivalence and precision of knee cartilage morphometry between different segmentation teams, cartilage regions, and MR acquisitions. Osteoarthritis Cartilage 20:869–879.
17. Kellgren JH, Lawrence JS. 1957. Radiological assessment of osteo-arthrosis. Ann Rheum Dis 16:494–502.
18. Bouhrara M, Bonny JM, Ashinsky BA, et al. 2017. Noise estimation and reduction in magnetic resonance imaging using a new multispectral nonlocal maximum-likelihood filter. IEEE Trans Med Imaging 36:181–193.
19. Bearer EL, Zhang X, Janvelyan D, et al. 2009. Reward circuitry is perturbed in the absence of the serotonin transporter. Neuroimage 46:1091–1104.
20. Chan KC, Fu QL, Hui ES, et al. 2008. Evaluation of the retina and optic nerve in a rat model of chronic glaucoma using in vivo manganese-enhanced magnetic resonance imaging. Neuroimage 40:1166–1174.
21. Chuang KH, Lee JH, Silva AC, et al. 2009. Manganese enhanced MRI reveals functional circuitry in response to odorant stimuli. Neuroimage 44:363–372.
22. Tucciarone J, Chuang KH, Dodd SJ, et al. 2009. Layer specific tracing of corticocortical and thalamocortical connectivity in the rodent using manganese enhanced MRI. Neuroimage 44:923–931.
23. Woods RP, Grafton ST, Holmes CJ, et al. 1998. Automated image registration: I. General methods and intrasubject, intramodality validation. J Comput Assist Tomogr 22:139–152.
24. Woods RP, Grafton ST, Watson JD, et al. 1998. Automated image registration: II. Intersubject validation of linear and nonlinear models. J Comput Assist Tomogr 22:153–165.
25. Bouhrara M, Reiter DA, Celik H, et al. 2015. Incorporation of Rician noise in the analysis of biexponential transverse relaxation in cartilage using a multiple gradient echo sequence at 3 and 7 tesla. Magn Reson Med 1:352–366.
26. Raya JG, Dietrich O, Horng A, et al. 2010. T2 measurement in articular cartilage: impact of the fitting method on accuracy and precision at low SNR. Magn Reson Med 63:181–193.
27. Hennig J. 1991. Echoes—how to generate, recognize, use or avoid them in MR-imaging sequences. Concepts Magn Reson 3:125–142.
28. Prasloski T, Madler B, Xiang QS, et al. 2012. Applications of stimulated echo correction to multicomponent T2 analysis. Magn Reson Med 67:1803–1814.
29. Bouhrara M, Bonny JM. 2012. B1 mapping with selective pulses. Magn Reson Med 68:1472–1480.
30. Simmons A, Tofts PS, Barker GJ, et al. 1994. Sources of intensity nonuniformity in spin echo images at 1.5 T. Magn Reson Med 32:121–128.
31. Orlov N, Shamir L, Macura T, et al. 2008. WND-CHARM: multi-purpose image classification using compound image transforms. Pattern Recognit Lett 29:1684–1693.
32. Shamir L, Ling SM, Scott WW Jr., et al. 2009. Knee x-ray image analysis method for automated detection of osteoarthritis. IEEE Trans Biomed Eng 56:407–415.
33. Pelletier JP, Raynauld JP, Berthiaume MJ, et al. 2007. Risk factors associated with the loss of cartilage volume on weight-bearing areas in knee osteoarthritis patients assessed by quantitative magnetic resonance imaging: a longitudinal study. Arthritis Res Ther 9:R74.
34. Eckstein F, Maschek S, Wirth W, et al. 2009. One year change of knee cartilage morphology in the first release of participants from the osteoarthritis initiative progression subcohort: association with sex, body mass index, symptoms and radiographic osteoarthritis status. Ann Rheum Dis 68:674–679.
35. Matzat SJ, van Tiel J, Gold GE, et al. 2013. Quantitative MRI techniques of cartilage composition. Quant Imaging Med Surg 3:162–174.
36. Choi JA, Gold GE. 2011. MR imaging of articular cartilage physiology. Magn Reson Imaging Clin N Am 19:249–282.
37. David-Vaudey E, Ghosh S, Ries M, et al. 2004. T2 relaxation time measurements in osteoarthritis. Magn Reson Imaging 22:673–682.
38. Spencer RG, Pleshko N. 2013. How do statistical differences in matrix-sensitive magnetic resonance outcomes translate into clinical assignment rules? J Am Acad Orthop Surg 21:438–439.
39. Spencer RG, Cortese BD, Lukas VA, et al. 2017. Point estimates of test sensitivity and specificity from sample means and variances. Am Stat In Press.
40. Boniatis I, Cavouras D, Costaridou L, et al. 2007. Computer-aided grading and quantification of hip osteoarthritis severity employing shape descriptors of radiographic hip joint space. Comput Biol Med 37:1786–1795.
41. Lin PC, Irrechukwu O, Roque R, et al. 2012. Multivariate analysis of cartilage degradation using the support vector machine algorithm. Magn Reson Med 67:1815–1826.
42. Lin PC, Reiter DA, Spencer RG. 2009. Classification of degraded cartilage through multiparametric MRI analysis. J Magn Reson 201:61–71.
43. Wang L, Nissi MJ, Toth F, et al. 2015. Multiparametric MRI of epiphyseal cartilage necrosis (osteochondrosis) with histological validation in a goat model. PLoS ONE 10:e0140400.
44. Rautiainen J, Nissi MJ, Salo EN, et al. 2014. Multiparametric MRI assessment of human articular cartilage degeneration: correlation with quantitative histology and mechanical properties. Magn Reson Med 74:249–259.
45. Griebel AJ, Trippel SB, Emery NC, et al. 2014. Noninvasive assessment of osteoarthritis severity in human explants by multicontrast MRI. Magn Reson Med 71:807–814.