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

Beth G. Ashinsky, Mustapha Bouhrara, Christopher E. Coletta, Benoit Lehallier, Kenneth L. Urish, Ping-Chang Lin, Ilya G. Goldberg, Richard G. Spencer

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

The purpose of this study is to evaluate the ability of a machine learning algorithm to classify in vivo magnetic resonance images (MRI) of human articular cartilage for development of osteoarthritis (OA). Sixty-eight subjects were selected from the osteoarthritis initiative (OAI) control and incidence cohorts. Progression to clinical OA was defined by the development of symptoms as quantified by the Western Ontario and McMaster Universities Arthritis (WOMAC) questionnaire 3 years after baseline evaluation. Multi-slice T2-weighted knee images, obtained through the OAI, of these subjects were registered using a nonlinear image registration algorithm. T2 maps of cartilage from the central weight bearing slices of the medial femoral condyle were derived from the registered images using the multiple available echo times and were classified for “progression to symptomatic OA” using the machine learning tool, weighted neighbor distance using compound hierarchy of algorithms representing morphology (WND-CHRM). WND-CHRM classified the isolated T2 maps for the progression to symptomatic OA with 75% accuracy. Clinical significance: Machine learning algorithms applied to T2 maps have the potential to provide important prognostic information for the development of OA.

Original languageEnglish (US)
Pages (from-to)2243-2250
Number of pages8
JournalJournal of Orthopaedic Research
Volume35
Issue number10
DOIs
StatePublished - Oct 1 2017
Externally publishedYes

Fingerprint

Osteoarthritis
Knee
Magnetic Resonance Spectroscopy
Weight-Bearing
Articular Cartilage
Ontario
Thigh
Machine Learning
Arthritis
Cartilage
Bone and Bones
Incidence

Keywords

  • MRI
  • classification
  • osteoarthritis
  • pattern recognition
  • registration
  • segmentation

ASJC Scopus subject areas

  • Orthopedics and Sports Medicine

Cite this

Predicting early symptomatic osteoarthritis in the human knee using machine learning classification of magnetic resonance images from the osteoarthritis initiative. / Ashinsky, Beth G.; Bouhrara, Mustapha; Coletta, Christopher E.; Lehallier, Benoit; Urish, Kenneth L.; Lin, Ping-Chang; Goldberg, Ilya G.; Spencer, Richard G.

In: Journal of Orthopaedic Research, Vol. 35, No. 10, 01.10.2017, p. 2243-2250.

Research output: Contribution to journalArticle

Ashinsky, Beth G. ; Bouhrara, Mustapha ; Coletta, Christopher E. ; Lehallier, Benoit ; Urish, Kenneth L. ; Lin, Ping-Chang ; Goldberg, Ilya G. ; Spencer, Richard G. / Predicting early symptomatic osteoarthritis in the human knee using machine learning classification of magnetic resonance images from the osteoarthritis initiative. In: Journal of Orthopaedic Research. 2017 ; Vol. 35, No. 10. pp. 2243-2250.
@article{980974b5c6014dfba6c3b53f115752da,
title = "Predicting early symptomatic osteoarthritis in the human knee using machine learning classification of magnetic resonance images from the osteoarthritis initiative",
abstract = "The purpose of this study is to evaluate the ability of a machine learning algorithm to classify in vivo magnetic resonance images (MRI) of human articular cartilage for development of osteoarthritis (OA). Sixty-eight subjects were selected from the osteoarthritis initiative (OAI) control and incidence cohorts. Progression to clinical OA was defined by the development of symptoms as quantified by the Western Ontario and McMaster Universities Arthritis (WOMAC) questionnaire 3 years after baseline evaluation. Multi-slice T2-weighted knee images, obtained through the OAI, of these subjects were registered using a nonlinear image registration algorithm. T2 maps of cartilage from the central weight bearing slices of the medial femoral condyle were derived from the registered images using the multiple available echo times and were classified for “progression to symptomatic OA” using the machine learning tool, weighted neighbor distance using compound hierarchy of algorithms representing morphology (WND-CHRM). WND-CHRM classified the isolated T2 maps for the progression to symptomatic OA with 75{\%} accuracy. Clinical significance: Machine learning algorithms applied to T2 maps have the potential to provide important prognostic information for the development of OA.",
keywords = "MRI, classification, osteoarthritis, pattern recognition, registration, segmentation",
author = "Ashinsky, {Beth G.} and Mustapha Bouhrara and Coletta, {Christopher E.} and Benoit Lehallier and Urish, {Kenneth L.} and Ping-Chang Lin and Goldberg, {Ilya G.} and Spencer, {Richard G.}",
year = "2017",
month = "10",
day = "1",
doi = "10.1002/jor.23519",
language = "English (US)",
volume = "35",
pages = "2243--2250",
journal = "Journal of Orthopaedic Research",
issn = "0736-0266",
publisher = "John Wiley and Sons Inc.",
number = "10",

}

TY - JOUR

T1 - Predicting early symptomatic osteoarthritis in the human knee using machine learning classification of magnetic resonance images from the osteoarthritis initiative

AU - Ashinsky, Beth G.

AU - Bouhrara, Mustapha

AU - Coletta, Christopher E.

AU - Lehallier, Benoit

AU - Urish, Kenneth L.

AU - Lin, Ping-Chang

AU - Goldberg, Ilya G.

AU - Spencer, Richard G.

PY - 2017/10/1

Y1 - 2017/10/1

N2 - The purpose of this study is to evaluate the ability of a machine learning algorithm to classify in vivo magnetic resonance images (MRI) of human articular cartilage for development of osteoarthritis (OA). Sixty-eight subjects were selected from the osteoarthritis initiative (OAI) control and incidence cohorts. Progression to clinical OA was defined by the development of symptoms as quantified by the Western Ontario and McMaster Universities Arthritis (WOMAC) questionnaire 3 years after baseline evaluation. Multi-slice T2-weighted knee images, obtained through the OAI, of these subjects were registered using a nonlinear image registration algorithm. T2 maps of cartilage from the central weight bearing slices of the medial femoral condyle were derived from the registered images using the multiple available echo times and were classified for “progression to symptomatic OA” using the machine learning tool, weighted neighbor distance using compound hierarchy of algorithms representing morphology (WND-CHRM). WND-CHRM classified the isolated T2 maps for the progression to symptomatic OA with 75% accuracy. Clinical significance: Machine learning algorithms applied to T2 maps have the potential to provide important prognostic information for the development of OA.

AB - The purpose of this study is to evaluate the ability of a machine learning algorithm to classify in vivo magnetic resonance images (MRI) of human articular cartilage for development of osteoarthritis (OA). Sixty-eight subjects were selected from the osteoarthritis initiative (OAI) control and incidence cohorts. Progression to clinical OA was defined by the development of symptoms as quantified by the Western Ontario and McMaster Universities Arthritis (WOMAC) questionnaire 3 years after baseline evaluation. Multi-slice T2-weighted knee images, obtained through the OAI, of these subjects were registered using a nonlinear image registration algorithm. T2 maps of cartilage from the central weight bearing slices of the medial femoral condyle were derived from the registered images using the multiple available echo times and were classified for “progression to symptomatic OA” using the machine learning tool, weighted neighbor distance using compound hierarchy of algorithms representing morphology (WND-CHRM). WND-CHRM classified the isolated T2 maps for the progression to symptomatic OA with 75% accuracy. Clinical significance: Machine learning algorithms applied to T2 maps have the potential to provide important prognostic information for the development of OA.

KW - MRI

KW - classification

KW - osteoarthritis

KW - pattern recognition

KW - registration

KW - segmentation

UR - http://www.scopus.com/inward/record.url?scp=85016411648&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85016411648&partnerID=8YFLogxK

U2 - 10.1002/jor.23519

DO - 10.1002/jor.23519

M3 - Article

C2 - 28084653

AN - SCOPUS:85016411648

VL - 35

SP - 2243

EP - 2250

JO - Journal of Orthopaedic Research

JF - Journal of Orthopaedic Research

SN - 0736-0266

IS - 10

ER -