Classification of degraded cartilage through multiparametric MRI analysis

Ping-Chang Lin, David A. Reiter, Richard G. Spencer

Research output: Contribution to journalArticle

35 Citations (Scopus)

Abstract

MRI analysis of cartilage matrix may play an important role in early detection and development of therapeutic protocols for degenerative joint disease. Correlations between MRI parameters and matrix integrity have been established in many studies, but the substantial overlap in values observed for normal and for degraded cartilage greatly limits the specificity of these analyses. We implemented established multiparametric analysis methods to define data clusters corresponding to control and degraded bovine nasal cartilage in two-, three-, and four-dimensional parameter spaces, and applied these results to discriminant analysis of a validation data set. Analyses were performed using the parameters (T1, T2, km, ADC), where km is the magnetization transfer rate and ADC is the apparent diffusion coefficient. Results were compared to univariate analyses. Multiparametric k-means clustering led to no improvement over univariate analyses, with a maximum sensitivity and specificity in the range of 60-70% for the detection of degradation using T1, and in the range of 80% sensitivity but only 36% specificity using the parameter pair (T1, km). In contrast, model-based analysis using more general Gaussian clusters resulted in markedly improved classification, with sensitivity and specificity reaching levels of 80-90% using the pair (T1, km). Finally, a fuzzy clustering technique was implemented which may be still more appropriate to the continuum of degradation seen in degenerative cartilage disease. In view of its success in identifying mild cartilage degradation, the formal multiparametric approach implemented here may be applicable to the nondestructive evaluation of other biomaterials using MRI.

Original languageEnglish (US)
Pages (from-to)61-71
Number of pages11
JournalJournal of Magnetic Resonance
Volume201
Issue number1
DOIs
StatePublished - Nov 1 2009
Externally publishedYes

Fingerprint

cartilage
Cartilage
Magnetic resonance imaging
Cluster Analysis
Nasal Cartilages
Cartilage Diseases
Sensitivity and Specificity
degradation
Degradation
Biocompatible Materials
Discriminant Analysis
sensitivity
Osteoarthritis
Reference Values
Fuzzy clustering
Discriminant analysis
matrices
integrity
Magnetization
diffusion coefficient

Keywords

  • Classification
  • Clustering
  • Multiparametric
  • Osteoarthritis
  • Sensitivity
  • Specificity

ASJC Scopus subject areas

  • Biophysics
  • Biochemistry
  • Nuclear and High Energy Physics
  • Condensed Matter Physics

Cite this

Classification of degraded cartilage through multiparametric MRI analysis. / Lin, Ping-Chang; Reiter, David A.; Spencer, Richard G.

In: Journal of Magnetic Resonance, Vol. 201, No. 1, 01.11.2009, p. 61-71.

Research output: Contribution to journalArticle

Lin, Ping-Chang ; Reiter, David A. ; Spencer, Richard G. / Classification of degraded cartilage through multiparametric MRI analysis. In: Journal of Magnetic Resonance. 2009 ; Vol. 201, No. 1. pp. 61-71.
@article{97fa4bfa457d47bf826910bae405703a,
title = "Classification of degraded cartilage through multiparametric MRI analysis",
abstract = "MRI analysis of cartilage matrix may play an important role in early detection and development of therapeutic protocols for degenerative joint disease. Correlations between MRI parameters and matrix integrity have been established in many studies, but the substantial overlap in values observed for normal and for degraded cartilage greatly limits the specificity of these analyses. We implemented established multiparametric analysis methods to define data clusters corresponding to control and degraded bovine nasal cartilage in two-, three-, and four-dimensional parameter spaces, and applied these results to discriminant analysis of a validation data set. Analyses were performed using the parameters (T1, T2, km, ADC), where km is the magnetization transfer rate and ADC is the apparent diffusion coefficient. Results were compared to univariate analyses. Multiparametric k-means clustering led to no improvement over univariate analyses, with a maximum sensitivity and specificity in the range of 60-70{\%} for the detection of degradation using T1, and in the range of 80{\%} sensitivity but only 36{\%} specificity using the parameter pair (T1, km). In contrast, model-based analysis using more general Gaussian clusters resulted in markedly improved classification, with sensitivity and specificity reaching levels of 80-90{\%} using the pair (T1, km). Finally, a fuzzy clustering technique was implemented which may be still more appropriate to the continuum of degradation seen in degenerative cartilage disease. In view of its success in identifying mild cartilage degradation, the formal multiparametric approach implemented here may be applicable to the nondestructive evaluation of other biomaterials using MRI.",
keywords = "Classification, Clustering, Multiparametric, Osteoarthritis, Sensitivity, Specificity",
author = "Ping-Chang Lin and Reiter, {David A.} and Spencer, {Richard G.}",
year = "2009",
month = "11",
day = "1",
doi = "10.1016/j.jmr.2009.08.001",
language = "English (US)",
volume = "201",
pages = "61--71",
journal = "Journal of Magnetic Resonance",
issn = "1090-7807",
publisher = "Academic Press Inc.",
number = "1",

}

TY - JOUR

T1 - Classification of degraded cartilage through multiparametric MRI analysis

AU - Lin, Ping-Chang

AU - Reiter, David A.

AU - Spencer, Richard G.

PY - 2009/11/1

Y1 - 2009/11/1

N2 - MRI analysis of cartilage matrix may play an important role in early detection and development of therapeutic protocols for degenerative joint disease. Correlations between MRI parameters and matrix integrity have been established in many studies, but the substantial overlap in values observed for normal and for degraded cartilage greatly limits the specificity of these analyses. We implemented established multiparametric analysis methods to define data clusters corresponding to control and degraded bovine nasal cartilage in two-, three-, and four-dimensional parameter spaces, and applied these results to discriminant analysis of a validation data set. Analyses were performed using the parameters (T1, T2, km, ADC), where km is the magnetization transfer rate and ADC is the apparent diffusion coefficient. Results were compared to univariate analyses. Multiparametric k-means clustering led to no improvement over univariate analyses, with a maximum sensitivity and specificity in the range of 60-70% for the detection of degradation using T1, and in the range of 80% sensitivity but only 36% specificity using the parameter pair (T1, km). In contrast, model-based analysis using more general Gaussian clusters resulted in markedly improved classification, with sensitivity and specificity reaching levels of 80-90% using the pair (T1, km). Finally, a fuzzy clustering technique was implemented which may be still more appropriate to the continuum of degradation seen in degenerative cartilage disease. In view of its success in identifying mild cartilage degradation, the formal multiparametric approach implemented here may be applicable to the nondestructive evaluation of other biomaterials using MRI.

AB - MRI analysis of cartilage matrix may play an important role in early detection and development of therapeutic protocols for degenerative joint disease. Correlations between MRI parameters and matrix integrity have been established in many studies, but the substantial overlap in values observed for normal and for degraded cartilage greatly limits the specificity of these analyses. We implemented established multiparametric analysis methods to define data clusters corresponding to control and degraded bovine nasal cartilage in two-, three-, and four-dimensional parameter spaces, and applied these results to discriminant analysis of a validation data set. Analyses were performed using the parameters (T1, T2, km, ADC), where km is the magnetization transfer rate and ADC is the apparent diffusion coefficient. Results were compared to univariate analyses. Multiparametric k-means clustering led to no improvement over univariate analyses, with a maximum sensitivity and specificity in the range of 60-70% for the detection of degradation using T1, and in the range of 80% sensitivity but only 36% specificity using the parameter pair (T1, km). In contrast, model-based analysis using more general Gaussian clusters resulted in markedly improved classification, with sensitivity and specificity reaching levels of 80-90% using the pair (T1, km). Finally, a fuzzy clustering technique was implemented which may be still more appropriate to the continuum of degradation seen in degenerative cartilage disease. In view of its success in identifying mild cartilage degradation, the formal multiparametric approach implemented here may be applicable to the nondestructive evaluation of other biomaterials using MRI.

KW - Classification

KW - Clustering

KW - Multiparametric

KW - Osteoarthritis

KW - Sensitivity

KW - Specificity

UR - http://www.scopus.com/inward/record.url?scp=70349728783&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70349728783&partnerID=8YFLogxK

U2 - 10.1016/j.jmr.2009.08.001

DO - 10.1016/j.jmr.2009.08.001

M3 - Article

C2 - 19762258

AN - SCOPUS:70349728783

VL - 201

SP - 61

EP - 71

JO - Journal of Magnetic Resonance

JF - Journal of Magnetic Resonance

SN - 1090-7807

IS - 1

ER -