Evaluation of an automated laminar cartilage T2 relaxation time analysis method in an early osteoarthritis model.

Cartilage T2 Deep learning Knee MRI Osteoarthritis U-Net

Journal

Skeletal radiology
ISSN: 1432-2161
Titre abrégé: Skeletal Radiol
Pays: Germany
ID NLM: 7701953

Informations de publication

Date de publication:
04 Sep 2024
Historique:
received: 03 07 2024
accepted: 27 08 2024
revised: 26 08 2024
medline: 4 9 2024
pubmed: 4 9 2024
entrez: 4 9 2024
Statut: aheadofprint

Résumé

A fully automated laminar cartilage composition (MRI-based T2) analysis method was technically and clinically validated by comparing radiographically normal knees with (CL-JSN) and without contra-lateral joint space narrowing or other signs of radiographic osteoarthritis (OA, CL-noROA). 2D U-Nets were trained from manually segmented femorotibial cartilages (n = 72) from all 7 echoes (All The agreement (Dice similarity coefficient) between automated vs. manual expert cartilage segmentation was between 0.82 ± 0.05/0.79 ± 0.06 (All The fully automated T2 analysis showed a high agreement, acceptable accuracy, and similar sensitivity to cross-sectional and longitudinal laminar T2 differences in an early OA model, compared with manual expert analysis. Clinicaltrials.gov identification: NCT00080171.

Identifiants

pubmed: 39230576
doi: 10.1007/s00256-024-04786-1
pii: 10.1007/s00256-024-04786-1
doi:

Banques de données

ClinicalTrials.gov
['NCT00080171']

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Subventions

Organisme : Eurostars
ID : E! 114932
Organisme : NIH HHS
ID : N01AR22258
Pays : United States
Organisme : NIH HHS
ID : N01AR22259
Pays : United States
Organisme : NIH HHS
ID : N01AR22260
Pays : United States
Organisme : NIH HHS
ID : N01AR22261
Pays : United States
Organisme : NIH HHS
ID : N01AR22262
Pays : United States
Organisme : Bundesministerium für Bildung und Forschung
ID : 01EC1408D

Informations de copyright

© 2024. The Author(s).

Références

Katz JN, Arant KR, Loeser RF. Diagnosis and treatment of hip and knee osteoarthritis: a review. JAMA - J Am Med Assoc. 2021;325(6):568–78.
doi: 10.1001/jama.2020.22171
Vos T, Abajobir AA, Abbafati C, et al. Global, regional, and national incidence, prevalence, and years lived with disability for 328 diseases and injuries for 195 countries, 1990–2016: a systematic analysis for the Global Burden of Disease Study 2016. Lancet. 2017;390(10100):1211–59.
doi: 10.1016/S0140-6736(17)32154-2
Turkiewicz A, Petersson IF, Björk J, et al. Current and future impact of osteoarthritis on health care: a population-based study with projections to year 2032. Osteoarthr Cartil. 2014;22(11):1826–32.
doi: 10.1016/j.joca.2014.07.015
Metcalfe AJ, Andersson MLE, Goodfellow R, Thorstensson CA. Is knee osteoarthritis a symmetrical disease? Analysis of a 12 year prospective cohort study. BMC Musculoskelet Disord. 2012;13:153.
doi: 10.1186/1471-2474-13-153 pubmed: 22917179 pmcid: 3485166
Spector TD, Hart DJ, Doyle DV. Incidence and progression of osteoarthritis in women with unilateral knee disease in the general population: the effect of obesity. Ann Rheum Dis. 1994;53(9):565–8.
doi: 10.1136/ard.53.9.565 pubmed: 7979593 pmcid: 1005406
Eckstein F, Maschek S, Roemer FW, Duda GN, Sharma L, Wirth W. Cartilage loss in radiographically normal knees depends on radiographic status of the contralateral knee – data from the Osteoarthritis Initiative. Osteoarthr Cartil. 2019;27(2):273–7.
doi: 10.1016/j.joca.2018.10.006
MacKay JW, Low SBL, Smith TO, Toms AP, McCaskie AW, Gilbert FJ. Systematic review and meta-analysis of the reliability and discriminative validity of cartilage compositional MRI in knee osteoarthritis. Osteoarthr Cartil. 2018;26(9):1140–52.
doi: 10.1016/j.joca.2017.11.018
Mosher TJ, Dardzinski BJ. Cartilage MRI T2 relaxation time mapping: overview and applications. SeminMusculoskeletRadiol. 2004;8(4):355–68.
Liess C, Luesse S, Karger N, Heller M, Glueer CC. Detection of changes in cartilage water content using MRI T2-mapping in vivo. OsteoarthritisCartilage. 2002;10:907–13.
Wirth W, Maschek S, Roemer FW, Sharma L, Duda GN, Eckstein F. Radiographically normal knees with contralateral joint space narrowing display greater change in cartilage transverse relaxation time than those with normal contralateral knees: a model of early OA? – data from the Osteoarthritis Initiative (OAI). Osteoarthr Cartil. 2019;27(11):1663–8.
doi: 10.1016/j.joca.2019.06.013
Ebrahimkhani S, Jaward MH, Cicuttini FM, Dharmaratne A, Wang Y, de Herrera AGS. A review on segmentation of knee articular cartilage: from conventional methods towards deep learning. Artif Intell Med. 2020;106(February):101851.
doi: 10.1016/j.artmed.2020.101851 pubmed: 32593389
Desai AD, Caliva F, Iriondo C, et al. The international workshop on osteoarthritis imaging knee mri segmentation challenge: a multi-institute evaluation and analysis framework on a standardized dataset. Radiol Artif Intell. 2021;3(3):1–13.
doi: 10.1148/ryai.2021200078
Wirth W, Eckstein F, Kemnitz J, et al. Accuracy and longitudinal reproducibility of quantitative femorotibial cartilage measures derived from automated U-Net-based segmentation of two different MRI contrasts: data from the osteoarthritis initiative healthy reference cohort. MAGMA. 2021;34(3):337–54.
doi: 10.1007/s10334-020-00889-7 pubmed: 33025284
Eckstein F, Chaudhari AS, Fuerst D, et al. Detection of differences in longitudinal cartilage thickness loss using a deep-learning automated segmentation algorithm: data from the Foundation for the National Institutes of Health Biomarkers Study of the Osteoarthritis Initiative. Arthritis Care Res (Hoboken). 2022;74(6):929–36.
doi: 10.1002/acr.24539 pubmed: 33337584
Thomas KA, Krzemiński D, Kidziński Ł, et al. Open source software for automatic subregional assessment of knee cartilage degradation using quantitative T2 relaxometry and deep learning. Cartilage. 2021;13(1_suppl):747S-756S.
doi: 10.1177/19476035211042406 pubmed: 34496667 pmcid: 8808775
Liu F, Zhou Z, Jang H, Samsonov A, Zhao G, Kijowski R. Deep convolutional neural network and 3D deformable approach for tissue segmentation in musculoskeletal magnetic resonance imaging. Magn Reson Med. 2018;79(4):2379–91.
doi: 10.1002/mrm.26841 pubmed: 28733975
Razmjoo A, Caliva F, Lee J, et al. T2 analysis of the entire osteoarthritis initiative dataset. J Orthop Res. 2021;39(1):74–85.
doi: 10.1002/jor.24811 pubmed: 32691905
Eckstein F, Wirth W, Nevitt MC. Recent advances in osteoarthritis imaging-the osteoarthritis initiative. Nat Rev Rheumatol. 2012;8(10):622–30.
doi: 10.1038/nrrheum.2012.113 pubmed: 22782003 pmcid: 6459017
Wirth W, Maschek S, Roemer FW, Eckstein F. Layer-specific femorotibial cartilage T2 relaxation time in knees with and without early knee osteoarthritis: data from the Osteoarthritis Initiative (OAI). Sci Rep. 2016;6:34202.
doi: 10.1038/srep34202 pubmed: 27670272 pmcid: 5037443
Peterfy CG, Schneider E, Nevitt M. The osteoarthritis initiative: report on the design rationale for the magnetic resonance imaging protocol for the knee. Osteoarthr Cartil. 2008;16(12):1433–41.
doi: 10.1016/j.joca.2008.06.016
Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation. In: Int. Conf. Med. image Comput. Comput. Interv. pp 234–241. https://doi.org/10.1007/978-3-319-24574-4_28
Wirth W, Maschek S, Eckstein F. Sex- and age-dependence of region- and layer-specific knee cartilage composition (spin–spin–relaxation time) in healthy reference subjects. Ann Anat - Anat Anzeiger. 2017;210(March):1–8.
Wirth W, Maschek S, Beringer P, Eckstein F. Subregional laminar cartilage MR spin-spin relaxation times (T2) in osteoarthritic knees with and without medial femorotibial cartilage loss - data from the Osteoarthritis Initiative (OAI). Osteoarthr Cartil. 2017;25(8):1313–23.
doi: 10.1016/j.joca.2017.03.013
Reinke A, Tizabi MD, Baumgartner M, et al. Understanding metric-related pitfalls in image analysis validation. Nat Methods. 2024;21(2):182–94.
doi: 10.1038/s41592-023-02150-0 pubmed: 38347140 pmcid: 11181963
Sharma L, Chmiel JS, Almagor O, et al. Significance of preradiographic magnetic resonance imaging lesions in persons at increased risk of knee osteoarthritis. Arthritis Rheumatol. 2014;66(7):1811–9.
doi: 10.1002/art.38611 pubmed: 24974824 pmcid: 4162852
Jungmann PM, Kraus MS, Nardo L, et al. T2 relaxation time measurements are limited in monitoring progression, once advanced cartilage defects at the knee occur: longitudinal data from the osteoarthritis initiative. JMagn Reson. 2013;38(6):1415–24.

Auteurs

Wolfgang Wirth (W)

Chondrometrics GmbH, Freilassing, Germany. wolfgang.wirth@pmu.ac.at.
Research Program for Musculoskeletal Imaging, Institute of Imaging & Functional Musculoskeletal Research, Center of Anatomy & Cell Biology, Paracelsus Medical University, Strubergasse 21, 5020, Salzburg, Austria. wolfgang.wirth@pmu.ac.at.
Ludwig Boltzmann Inst. for Arthritis and Rehabilitation (LBIAR), Paracelsus Medical University, Strubergasse 21, 5020, Salzburg, Austria. wolfgang.wirth@pmu.ac.at.

Susanne Maschek (S)

Chondrometrics GmbH, Freilassing, Germany.
Research Program for Musculoskeletal Imaging, Institute of Imaging & Functional Musculoskeletal Research, Center of Anatomy & Cell Biology, Paracelsus Medical University, Strubergasse 21, 5020, Salzburg, Austria.

Anna Wisser (A)

Chondrometrics GmbH, Freilassing, Germany.
Research Program for Musculoskeletal Imaging, Institute of Imaging & Functional Musculoskeletal Research, Center of Anatomy & Cell Biology, Paracelsus Medical University, Strubergasse 21, 5020, Salzburg, Austria.
Ludwig Boltzmann Inst. for Arthritis and Rehabilitation (LBIAR), Paracelsus Medical University, Strubergasse 21, 5020, Salzburg, Austria.

Jana Eder (J)

Research Program for Musculoskeletal Imaging, Institute of Imaging & Functional Musculoskeletal Research, Center of Anatomy & Cell Biology, Paracelsus Medical University, Strubergasse 21, 5020, Salzburg, Austria.

Christian F Baumgartner (CF)

University of Tübingen, Tübingen, Germany.

Akshay Chaudhari (A)

Department of Radiology, Stanford University, Stanford, CA, USA.

Francis Berenbaum (F)

, 4Moving Biotech, Lille, France.
Department of Rheumatology, AP-HP Saint-Antoine Hospital, Paris, France.
Sorbonne University, AP-HP Saint-Antoine Hospital, INSERM, Paris, France.

Felix Eckstein (F)

Chondrometrics GmbH, Freilassing, Germany.
Research Program for Musculoskeletal Imaging, Institute of Imaging & Functional Musculoskeletal Research, Center of Anatomy & Cell Biology, Paracelsus Medical University, Strubergasse 21, 5020, Salzburg, Austria.
Ludwig Boltzmann Inst. for Arthritis and Rehabilitation (LBIAR), Paracelsus Medical University, Strubergasse 21, 5020, Salzburg, Austria.

Classifications MeSH