TY - JOUR
T1 - Multivariate analysis of cartilage degradation using the support vector machine algorithm
AU - Lin, Ping Chang
AU - Irrechukwu, Onyi
AU - Roque, Remy
AU - Hancock, Brynne
AU - Fishbein, Kenneth W.
AU - Spencer, Richard G.
N1 - Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.
PY - 2012/6
Y1 - 2012/6
N2 - An important limitation in MRI studies of early osteoarthritis is that measured MRI parameters exhibit substantial overlap between different degrees of cartilage degradation. We investigated whether multivariate support vector machine analysis would permit improved tissue characterization. Bovine nasal cartilage samples were subjected to pathomimetic degradation and their T 1, T2, magnetization transfer rate (km), and apparent diffusion coefficient (ADC) were measured. Support vector machine analysis performed using certain parameter combinations exhibited particularly favorable classification properties. The areas under the receiver operating characteristic (ROC) curve for detection of extensive and mild degradation were 1.00 and 0.94, respectively, using the set (T1, km, ADC), compared with 0.97 and 0.60 using T1, the best univariate classifier. Furthermore, a degradation probability for each sample, derived from the support vector machine formalism using the parameter set (T1, k m, ADC), demonstrated much stronger correlations (r2 = 0.79-0.88) with direct measurements of tissue biochemical components than did even the best-performing individual MRI parameter, T1 (r2 = 0.53-0.64). These results, combined with our previous investigation of Gaussian cluster-based tissue discrimination, indicate that the combinations (T1, km) and (T1, km, ADC) may emerge as particularly useful for characterization of early cartilage degradation.
AB - An important limitation in MRI studies of early osteoarthritis is that measured MRI parameters exhibit substantial overlap between different degrees of cartilage degradation. We investigated whether multivariate support vector machine analysis would permit improved tissue characterization. Bovine nasal cartilage samples were subjected to pathomimetic degradation and their T 1, T2, magnetization transfer rate (km), and apparent diffusion coefficient (ADC) were measured. Support vector machine analysis performed using certain parameter combinations exhibited particularly favorable classification properties. The areas under the receiver operating characteristic (ROC) curve for detection of extensive and mild degradation were 1.00 and 0.94, respectively, using the set (T1, km, ADC), compared with 0.97 and 0.60 using T1, the best univariate classifier. Furthermore, a degradation probability for each sample, derived from the support vector machine formalism using the parameter set (T1, k m, ADC), demonstrated much stronger correlations (r2 = 0.79-0.88) with direct measurements of tissue biochemical components than did even the best-performing individual MRI parameter, T1 (r2 = 0.53-0.64). These results, combined with our previous investigation of Gaussian cluster-based tissue discrimination, indicate that the combinations (T1, km) and (T1, km, ADC) may emerge as particularly useful for characterization of early cartilage degradation.
KW - MRI
KW - classification
KW - clustering
KW - discriminant analysis
KW - osteoarthritis
UR - http://www.scopus.com/inward/record.url?scp=84861234582&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84861234582&partnerID=8YFLogxK
U2 - 10.1002/mrm.23189
DO - 10.1002/mrm.23189
M3 - Article
C2 - 22179972
AN - SCOPUS:84861234582
SN - 0740-3194
VL - 67
SP - 1815
EP - 1826
JO - Magnetic Resonance in Medicine
JF - Magnetic Resonance in Medicine
IS - 6
ER -