Machine learning-augmented and microspectroscopy-informed multiparametric MRI for the non-invasive prediction of articular cartilage composition

Linka K, Thuering J, Rieppo L, Aydin RC, Cyron CJ, Kuhl CK, Merhof D, Truhn D, Nebelung S (2021)

Publication Type: Journal article

Publication year: 2021

Journal

Osteoarthritis and Cartilage Elsevier

Book Volume: 29

Pages Range: 592-602

Journal Issue: 4

DOI: 10.1016/j.joca.2020.12.022

Abstract

Background: Articular cartilage degeneration is the hallmark change of osteoarthritis, a severely disabling disease with high prevalence and considerable socioeconomic and individual burden. Early, potentially reversible cartilage degeneration is characterized by distinct changes in cartilage composition and ultrastructure, while the tissue's morphology remains largely unaltered. Hence, early degenerative changes may not be diagnosed by clinical standard diagnostic tools. Methods: Against this background, this study introduces a novel method to determine the tissue composition non-invasively. Our method involves quantitative MRI parameters (i.e., T1, T1ρ, T2 and T2∗ maps), compositional reference measurements (i.e., microspectroscopically determined local proteoglycan [PG] and collagen [CO] contents) and machine learning techniques (i.e., artificial neural networks [ANNs] and multivariate linear models [MLMs]) on 17 histologically grossly intact human cartilage samples. Results: Accuracy and precision were higher in ANN-based predictions than in MLM-based predictions and moderate-to-strong correlations were found between measured and predicted compositional parameters. Conclusion: Once trained for the clinical setting, advanced machine learning techniques, in particular ANNs, may be used to non-invasively determine compositional features of cartilage based on quantitative MRI parameters with potential implications for the diagnosis of (early) degeneration and for the monitoring of therapeutic outcomes.

Involved external institutions

Technische Universität Hamburg-Harburg (TUHH) DE Germany (DE) Universitätsklinikum Aachen (UKA) DE Germany (DE) Oulun Yliopisto / University of Oulo FI Finland (FI) Helmholtz-Zentrum Geesthacht Zentrum für Material- und Küstenforschung GmbH (HZG) DE Germany (DE) Rheinisch-Westfälische Technische Hochschule (RWTH) Aachen DE Germany (DE) Heinrich-Heine-Universität Düsseldorf DE Germany (DE)

How to cite

APA:

Linka, K., Thuering, J., Rieppo, L., Aydin, R.C., Cyron, C.J., Kuhl, C.K.,... Nebelung, S. (2021). Machine learning-augmented and microspectroscopy-informed multiparametric MRI for the non-invasive prediction of articular cartilage composition. Osteoarthritis and Cartilage, 29(4), 592-602. https://doi.org/10.1016/j.joca.2020.12.022

MLA:

Linka, K., et al. "Machine learning-augmented and microspectroscopy-informed multiparametric MRI for the non-invasive prediction of articular cartilage composition." Osteoarthritis and Cartilage 29.4 (2021): 592-602.

BibTeX: Download