Abstract
BACKGROUND: The variation in articular cartilage thickness (ACT) in healthy knees is difficult to quantify and therefore poorly documented. Our aims are to (1) define how machine learning (ML) algorithms can automate the segmentation and measurement of ACT on magnetic resonance imaging (MRI) (2) use ML to provide reference data on ACT in healthy knees, and (3) identify whether demographic variables impact these results. METHODS: Patients recruited into the Osteoarthritis Initiative with a radiographic Kellgren-Lawrence grade of 0 or 1 with 3D double-echo steady-state MRIs were included and their gender, age, and body mass index were collected. Using a validated ML algorithm, 2 orthogonal points on each femoral condyle were identified (distal and posterior) and ACT was measured on each MRI. Site-specific ACT was compared using paired t-tests, and multivariate regression was used to investigate the risk-adjusted effect of each demographic variable on ACT. RESULTS: A total of 3910 MRI were included. The average femoral ACT was 2.34 mm (standard deviation, 0.71; 95% confidence interval, 0.95-3.73). In multivariate analysis, distal-medial (-0.17 mm) and distal-lateral cartilage (-0.32 mm) were found to be thinner than posterior-lateral cartilage, while posterior-medial cartilage was found to be thicker (0.21 mm). In addition, female sex was found to negatively impact cartilage thickness (OR, -0.36; all values: P < .001). CONCLUSION: ML was effectively used to automate the segmentation and measurement of cartilage thickness on a large number of MRIs of healthy knees to provide normative data on the variation in ACT in this population. We further report patient variables that can influence ACT. Further validation will determine whether this technique represents a powerful new tool for tracking the impact of medical intervention on the progression of articular cartilage degeneration.