Evaluation of an automated laminar cartilage T2 relaxation time analysis method in an early osteoarthritis model
Authors:
- Wolfgang WirthWWWolfgang Wirth
- Susanne MaschekSMSusanne Maschek
- Anna WisserAWAnna Wisser
- Jana EderJEJana Eder
- Christian F. BaumgartnerCBChristian F. Baumgartner
- Akshay ChaudhariACAkshay Chaudhari
- Francis BerenbaumFBFrancis Berenbaum
- Felix EcksteinFEFelix Eckstein
- on behalf of the OA-BIO ConsortiumOCon behalf of the OA-BIO Consortium
Open Access
- 4 September 2024
- journal article
- research article
- Published by Springer Nature in Skeletal Radiology
- Vol. 54 (3) , 571-584
Abstract
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 (AllE), or from the 1st echo only (1st E) of multi-echo-spin-echo (MESE) MRIs acquired by the Osteoarthritis Initiative (OAI). Because of its greater accuracy, only the AllE 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 (AllE/1st E) and 0.88 ± 0.03/0.88 ± 0.03 (AllE/1st 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 (AllE/1st E). The AllE 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 AllE 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.Keywords
Funding Information
- Eurostars (E! 114932)
- National Institutes of Health (N01AR22258, N01AR22259, N01AR22260, N01AR22261, N01AR22262)
- Bundesministerium für Forschung, Technologie und Raumfahrt (01EC1408D)
- Paracelsus Medical University
This publication has 27 references indexed in Scilit:
- 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 InitiativeArthritis Care & Research, 2022
- 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 cohortMagnetic Resonance Materials in Physics, Biology and Medicine, 2020
- T2 analysis of the entire osteoarthritis initiative datasetJournal of Orthopaedic Research, 2020
- A review on segmentation of knee articular cartilage: from conventional methods towards deep learningArtificial Intelligence in Medicine, 2020
- Deep convolutional neural network and 3D deformable approach for tissue segmentation in musculoskeletal magnetic resonance imagingMagnetic Resonance in Medicine, 2017
- Layer-specific femorotibial cartilage T2 relaxation time in knees with and without early knee osteoarthritis: Data from the Osteoarthritis Initiative (OAI)Scientific Reports, 2016
- Significance of Preradiographic Magnetic Resonance Imaging Lesions in Persons at Increased Risk of Knee OsteoarthritisArthritis & Rheumatology, 2014
- Is knee osteoarthritis a symmetrical disease? Analysis of a 12 year prospective cohort studyBMC Musculoskeletal Disorders, 2012
- Recent advances in osteoarthritis imaging—the Osteoarthritis InitiativeNature Reviews Rheumatology, 2012
- Incidence and progression of osteoarthritis in women with unilateral knee disease in the general population: the effect of obesity.Annals of the Rheumatic Diseases, 1994