EUVIMEDEUVIMED entdecken
BeobachtungsstudieOpen Access · CC BY 4.0

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

Wolfgang Wirth, Susanne Maschek, Anna Wisser, Jana Eder, Christian F Baumgartner, Akshay Chaudhari, Francis Berenbaum, Felix Eckstein, OA-BIO Consortium

Skeletal Radiology · 2025

DOI: 10.1007/s00256-024-04786-1 ↗

Kurz gefasst

Beobachtungsstudie in der Zeitschrift Skeletal Radiology, 2025. Verfasst von Wolfgang Wirth und 8 weiteren Autor:innen. Beteiligte Einrichtung: Chondrometrics GmbH, Freilassing, Germany. wolfgang.wirth@pmu.ac.at. Hauptthemen laut MEDLINE: Cartilage, Articular, Image Interpretation, Computer-Assisted, Magnetic Resonance Imaging, Osteoarthritis, Knee. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIH HHS, Eurostars, Bundesministerium für Bildung und Forschung.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

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). Materials and methods 2D U-Nets were trained from manually segmented femorotibial cartilages ( n = 72) from all 7 echoes (All E ), or from the 1st echo only (1 st E ) of multi-echo-spin-echo (MESE) MRIs acquired by the Osteoarthritis Initiative (OAI). Because of its greater accuracy, only the All E U-Net was then applied to knees from the OAI healthy reference cohort ( n = 10), CL-JSN ( n = 39), and (1:1) matched CL-noROA knees ( n = 39) that all had manual expert segmentation, and to 982 non-matched CL-noROA knees without expert segmentation.

Results

The agreement (Dice similarity coefficient) between automated vs. manual expert cartilage segmentation was between 0.82 ± 0.05/0.79 ± 0.06 (All E /1 st E) and 0.88 ± 0.03/0.88 ± 0.03 (All E /1 st E ) across femorotibial cartilage plates. The deviation between automated vs. manually derived laminar T2 reached up to − 2.2 ± 2.6 ms/ + 4.1 ± 10.2 ms (All E /1 st E ). The All E U-Net showed a similar sensitivity to cross-sectional laminar T2 differences between CL-JSN and CL-noROA knees in the matched (Cohen’s D ≤ 0.54) and the non-matched ( D ≤ 0.54) comparison as the matched manual analyses ( D ≤ 0.48). Longitudinally, the All E U-Net also showed a similar sensitivity to CL-JSN vs. CS-noROA differences in the matched ( D ≤ 0.51) and the non-matched ( D ≤ 0.43) comparison as matched manual analyses ( D ≤ 0.41).

Conclusion

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.

Trial registration

Clinicaltrials.gov identification: NCT00080171.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Cartilage, ArticularImage Interpretation, Computer-AssistedMagnetic Resonance ImagingOsteoarthritis, KneeAgedFemaleHumansMaleMiddle AgedReproducibility of Results

Stichwörter der Autor:innen

Cartilage T2Deep learningKneeMRIOsteoarthritisU-Net

Autor:innen und Institutionen

  • 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. wolfga…
  • Ludwig Boltzmann Inst. for Arthritis and Rehabilitation (LBIAR), Paracelsus Medical University, Strubergasse 21, 5020, Salzburg, Austria. wolfgang.wirth@pmu.ac.at.
  • 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.

Förderung

  • NIH HHS
  • Eurostars
  • Bundesministerium für Bildung und Forschung
  • National Institutes of Health
  • Paracelsus Medical University

Zitieren

APA

Wirth, W., Maschek, S., Wisser, A., Eder, J., Baumgartner, C. F., Chaudhari, A., Berenbaum, F., Eckstein, F., & OA-BIO Consortium (2025). Evaluation of an automated laminar cartilage T2 relaxation time analysis method in an early osteoarthritis model. Skeletal Radiology. https://doi.org/10.1007/s00256-024-04786-1

Vancouver

Wirth W, Maschek S, Wisser A, Eder J, Baumgartner CF, Chaudhari A, et al. Evaluation of an automated laminar cartilage T2 relaxation time analysis method in an early osteoarthritis model. Skeletal Radiology. 2025. doi:10.1007/s00256-024-04786-1

BibTeX
@article{Wirth2025,
  author = {Wirth, Wolfgang and Maschek, Susanne and Wisser, Anna and Eder, Jana and Baumgartner, Christian F and Chaudhari, Akshay and Berenbaum, Francis and Eckstein, Felix and OA-BIO Consortium, OA-BIO Consortium},
  title = {Evaluation of an automated laminar cartilage T2 relaxation time analysis method in an early osteoarthritis model},
  journal = {Skeletal Radiology},
  year = {2025},
  doi = {10.1007/s00256-024-04786-1}
}
Kostenlos starten →