Multivariate analysis of cartilage degradation using the support vector machine algorithm

Ping-Chang Lin, Onyi Irrechukwu, Remy Roque, Brynne Hancock, Kenneth W. Fishbein, Richard G. Spencer

Research output: Contribution to journalArticle

23 Citations (Scopus)

Abstract

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.

Original languageEnglish (US)
Pages (from-to)1815-1826
Number of pages12
JournalMagnetic Resonance in Medicine
Volume67
Issue number6
DOIs
StatePublished - Jun 1 2012
Externally publishedYes

Fingerprint

Cartilage
Multivariate Analysis
Nasal Cartilages
Sampling Studies
ROC Curve
Osteoarthritis
Support Vector Machine

Keywords

  • MRI
  • classification
  • clustering
  • discriminant analysis
  • osteoarthritis

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging

Cite this

Lin, P-C., Irrechukwu, O., Roque, R., Hancock, B., Fishbein, K. W., & Spencer, R. G. (2012). Multivariate analysis of cartilage degradation using the support vector machine algorithm. Magnetic Resonance in Medicine, 67(6), 1815-1826. https://doi.org/10.1002/mrm.23189

Multivariate analysis of cartilage degradation using the support vector machine algorithm. / Lin, Ping-Chang; Irrechukwu, Onyi; Roque, Remy; Hancock, Brynne; Fishbein, Kenneth W.; Spencer, Richard G.

In: Magnetic Resonance in Medicine, Vol. 67, No. 6, 01.06.2012, p. 1815-1826.

Research output: Contribution to journalArticle

Lin, P-C, Irrechukwu, O, Roque, R, Hancock, B, Fishbein, KW & Spencer, RG 2012, 'Multivariate analysis of cartilage degradation using the support vector machine algorithm', Magnetic Resonance in Medicine, vol. 67, no. 6, pp. 1815-1826. https://doi.org/10.1002/mrm.23189
Lin, Ping-Chang ; Irrechukwu, Onyi ; Roque, Remy ; Hancock, Brynne ; Fishbein, Kenneth W. ; Spencer, Richard G. / Multivariate analysis of cartilage degradation using the support vector machine algorithm. In: Magnetic Resonance in Medicine. 2012 ; Vol. 67, No. 6. pp. 1815-1826.
@article{fff55fe75b8b4cc792d7a93e444b3fe3,
title = "Multivariate analysis of cartilage degradation using the support vector machine algorithm",
abstract = "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.",
keywords = "MRI, classification, clustering, discriminant analysis, osteoarthritis",
author = "Ping-Chang Lin and Onyi Irrechukwu and Remy Roque and Brynne Hancock and Fishbein, {Kenneth W.} and Spencer, {Richard G.}",
year = "2012",
month = "6",
day = "1",
doi = "10.1002/mrm.23189",
language = "English (US)",
volume = "67",
pages = "1815--1826",
journal = "Magnetic Resonance in Medicine",
issn = "0740-3194",
publisher = "John Wiley and Sons Inc.",
number = "6",

}

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.

PY - 2012/6/1

Y1 - 2012/6/1

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

VL - 67

SP - 1815

EP - 1826

JO - Magnetic Resonance in Medicine

JF - Magnetic Resonance in Medicine

SN - 0740-3194

IS - 6

ER -