Classification of histologically scored human knee osteochondral plugs by quantitative analysis of magnetic resonance images at 3T

Vanessa A. Lukas, Kenneth W. Fishbein, Ping-Chang Lin, Michael Schär, Erika Schneider, Corey P. Neu, Richard G. Spencer, David A. Reiter

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

This work evaluates the ability of quantitative MRI to discriminate between normal and pathological human osteochondral plugs characterized by the Osteoarthritis Research Society International (OARSI) histological system. Normal and osteoarthritic human osteochondral plugs were scored using the OARSI histological system and imaged at 3 T using MRI sequences producing T1 and T2 contrast and measuring T1, T2, and T2∗ relaxation times, magnetization transfer, and diffusion. The classification accuracies of quantitative MRI parameters and corresponding weighted image intensities were evaluated. Classification models based on the Mahalanobis distance metric for each MRI measurement were trained and validated using leave-one-out cross-validation with plugs grouped according to OARSI histological grade and score. MRI measurements used for classification were performed using a region-of-interest analysis which included superficial, deep, and full-thickness cartilage. The best classifiers based on OARSI grade and score were T1- and T2-weighted image intensities, which yielded accuracies of 0.68 and 0.75, respectively. Classification accuracies using OARSI score-based group membership were generally higher when compared with grade-based group membership. MRI-based classification - either using quantitative MRI parameters or weighted image intensities - is able to detect early osteoarthritic tissue changes as classified by the OARSI histological system. These findings suggest the benefit of incorporating quantitative MRI acquisitions in a comprehensive clinical evaluation of OA.

Original languageEnglish (US)
Pages (from-to)640-650
Number of pages11
JournalJournal of Orthopaedic Research
Volume33
Issue number5
DOIs
StatePublished - May 1 2015

Fingerprint

Osteoarthritis
Knee
Magnetic Resonance Spectroscopy
Research
Cartilage

Keywords

  • cartilage matrix
  • classification
  • imaging
  • osteoarthritis
  • quantitative MRI

ASJC Scopus subject areas

  • Orthopedics and Sports Medicine

Cite this

Classification of histologically scored human knee osteochondral plugs by quantitative analysis of magnetic resonance images at 3T. / Lukas, Vanessa A.; Fishbein, Kenneth W.; Lin, Ping-Chang; Schär, Michael; Schneider, Erika; Neu, Corey P.; Spencer, Richard G.; Reiter, David A.

In: Journal of Orthopaedic Research, Vol. 33, No. 5, 01.05.2015, p. 640-650.

Research output: Contribution to journalArticle

Lukas, VA, Fishbein, KW, Lin, P-C, Schär, M, Schneider, E, Neu, CP, Spencer, RG & Reiter, DA 2015, 'Classification of histologically scored human knee osteochondral plugs by quantitative analysis of magnetic resonance images at 3T', Journal of Orthopaedic Research, vol. 33, no. 5, pp. 640-650. https://doi.org/10.1002/jor.22810
Lukas, Vanessa A. ; Fishbein, Kenneth W. ; Lin, Ping-Chang ; Schär, Michael ; Schneider, Erika ; Neu, Corey P. ; Spencer, Richard G. ; Reiter, David A. / Classification of histologically scored human knee osteochondral plugs by quantitative analysis of magnetic resonance images at 3T. In: Journal of Orthopaedic Research. 2015 ; Vol. 33, No. 5. pp. 640-650.
@article{38548a10513048c3a5abe6971abbc279,
title = "Classification of histologically scored human knee osteochondral plugs by quantitative analysis of magnetic resonance images at 3T",
abstract = "This work evaluates the ability of quantitative MRI to discriminate between normal and pathological human osteochondral plugs characterized by the Osteoarthritis Research Society International (OARSI) histological system. Normal and osteoarthritic human osteochondral plugs were scored using the OARSI histological system and imaged at 3 T using MRI sequences producing T1 and T2 contrast and measuring T1, T2, and T2∗ relaxation times, magnetization transfer, and diffusion. The classification accuracies of quantitative MRI parameters and corresponding weighted image intensities were evaluated. Classification models based on the Mahalanobis distance metric for each MRI measurement were trained and validated using leave-one-out cross-validation with plugs grouped according to OARSI histological grade and score. MRI measurements used for classification were performed using a region-of-interest analysis which included superficial, deep, and full-thickness cartilage. The best classifiers based on OARSI grade and score were T1- and T2-weighted image intensities, which yielded accuracies of 0.68 and 0.75, respectively. Classification accuracies using OARSI score-based group membership were generally higher when compared with grade-based group membership. MRI-based classification - either using quantitative MRI parameters or weighted image intensities - is able to detect early osteoarthritic tissue changes as classified by the OARSI histological system. These findings suggest the benefit of incorporating quantitative MRI acquisitions in a comprehensive clinical evaluation of OA.",
keywords = "cartilage matrix, classification, imaging, osteoarthritis, quantitative MRI",
author = "Lukas, {Vanessa A.} and Fishbein, {Kenneth W.} and Ping-Chang Lin and Michael Sch{\"a}r and Erika Schneider and Neu, {Corey P.} and Spencer, {Richard G.} and Reiter, {David A.}",
year = "2015",
month = "5",
day = "1",
doi = "10.1002/jor.22810",
language = "English (US)",
volume = "33",
pages = "640--650",
journal = "Journal of Orthopaedic Research",
issn = "0736-0266",
publisher = "John Wiley and Sons Inc.",
number = "5",

}

TY - JOUR

T1 - Classification of histologically scored human knee osteochondral plugs by quantitative analysis of magnetic resonance images at 3T

AU - Lukas, Vanessa A.

AU - Fishbein, Kenneth W.

AU - Lin, Ping-Chang

AU - Schär, Michael

AU - Schneider, Erika

AU - Neu, Corey P.

AU - Spencer, Richard G.

AU - Reiter, David A.

PY - 2015/5/1

Y1 - 2015/5/1

N2 - This work evaluates the ability of quantitative MRI to discriminate between normal and pathological human osteochondral plugs characterized by the Osteoarthritis Research Society International (OARSI) histological system. Normal and osteoarthritic human osteochondral plugs were scored using the OARSI histological system and imaged at 3 T using MRI sequences producing T1 and T2 contrast and measuring T1, T2, and T2∗ relaxation times, magnetization transfer, and diffusion. The classification accuracies of quantitative MRI parameters and corresponding weighted image intensities were evaluated. Classification models based on the Mahalanobis distance metric for each MRI measurement were trained and validated using leave-one-out cross-validation with plugs grouped according to OARSI histological grade and score. MRI measurements used for classification were performed using a region-of-interest analysis which included superficial, deep, and full-thickness cartilage. The best classifiers based on OARSI grade and score were T1- and T2-weighted image intensities, which yielded accuracies of 0.68 and 0.75, respectively. Classification accuracies using OARSI score-based group membership were generally higher when compared with grade-based group membership. MRI-based classification - either using quantitative MRI parameters or weighted image intensities - is able to detect early osteoarthritic tissue changes as classified by the OARSI histological system. These findings suggest the benefit of incorporating quantitative MRI acquisitions in a comprehensive clinical evaluation of OA.

AB - This work evaluates the ability of quantitative MRI to discriminate between normal and pathological human osteochondral plugs characterized by the Osteoarthritis Research Society International (OARSI) histological system. Normal and osteoarthritic human osteochondral plugs were scored using the OARSI histological system and imaged at 3 T using MRI sequences producing T1 and T2 contrast and measuring T1, T2, and T2∗ relaxation times, magnetization transfer, and diffusion. The classification accuracies of quantitative MRI parameters and corresponding weighted image intensities were evaluated. Classification models based on the Mahalanobis distance metric for each MRI measurement were trained and validated using leave-one-out cross-validation with plugs grouped according to OARSI histological grade and score. MRI measurements used for classification were performed using a region-of-interest analysis which included superficial, deep, and full-thickness cartilage. The best classifiers based on OARSI grade and score were T1- and T2-weighted image intensities, which yielded accuracies of 0.68 and 0.75, respectively. Classification accuracies using OARSI score-based group membership were generally higher when compared with grade-based group membership. MRI-based classification - either using quantitative MRI parameters or weighted image intensities - is able to detect early osteoarthritic tissue changes as classified by the OARSI histological system. These findings suggest the benefit of incorporating quantitative MRI acquisitions in a comprehensive clinical evaluation of OA.

KW - cartilage matrix

KW - classification

KW - imaging

KW - osteoarthritis

KW - quantitative MRI

UR - http://www.scopus.com/inward/record.url?scp=84928204798&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84928204798&partnerID=8YFLogxK

U2 - 10.1002/jor.22810

DO - 10.1002/jor.22810

M3 - Article

C2 - 25641500

AN - SCOPUS:84928204798

VL - 33

SP - 640

EP - 650

JO - Journal of Orthopaedic Research

JF - Journal of Orthopaedic Research

SN - 0736-0266

IS - 5

ER -