Answers are grounded in this paper and cite their sources.
Objectives To evaluate the accuracy and reliability of automated Gaussian Mixture Modelling (GMM) and K-means clustering for intramuscular fat (IMF) quantification on T 2 -weighted (T 2 W) and intermediate-weighted (IW) shoulder MRI, using two-point Dixon as the reference standard. Materials & Methods This retrospective study collected MRI datasets of patients who underwent both two-point Dixon with T 2 W and/or IW shoulder MRI. GMM and K-means were applied to quantify IMF of the supraspinatus, subscapularis, infraspinatus, teres minor, and deltoid. Accuracy and reliability relative to Dixon were evaluated using Bland-Altman analysis and intraclass correlation coefficients (ICC 2,1 ). Raw IMF values from GMM, K-means and Dixon were compared using repeated-measures ANOVA with post-hoc Dunnett's test \( ∝ = 0.05 \) . Results Eighty patients (mean age, 58 years ± 15 [standard deviation]; 41 males) were evaluated. On T 2 W MRI, GMM outperformed K-means with a maximum mean bias of −3.07% and excellent reliability for supraspinatus, subscapularis, infraspinatus and deltoid (ICC 2,1 ≥ 0.90). K-means produced poor to moderate reliability. On IW MRI, GMM mean bias did not exceed −2.81% and showed excellent reliability for infraspinatus (ICC 2,1 = 0.92) with good reliability for other muscles. K-means showed higher bias (−4.36%) and lower reliability (ICC 2,1 ≤ 0.81) than GMM. GMM was the only model that did not significantly differ from Dixon IMF values on T 2 W ( p ≥ 0.074) and IW ( p ≥ 0.243) MRI. Conclusion IMF quantification using GMM thresholding achieves better agreement with Dixon IMF values than K-Means on T 2 W and IW MRI.
No takes yet. Share an insight, caveat, or question.
Kim et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: