From Kellgren-Lawrence to Calcium Pyrophosphate Crystal Deposition: A Soft-Labelling Framework for Knee Osteoarthritis Assessmen

2026-05-27

AI Summary

This study addresses the limitations of conventional deep learning approaches that employ one-hot labels for knee osteoarthritis grading, which fail to capture the ordinal uncertainty inherent in Kellgren–Lawrence (KL) and Calcium Pyrophosphate Deposition (CPPD) scoring systems and the clinically observed asymmetric relationships between adjacent grades. To overcome this, the work proposes the first soft-label ordinal deep learning framework tailored for multiscale assessment of knee osteoarthritis. It replaces hard one-hot labels with unimodal probability distributions—centered at the annotated grade—including binomial, beta, triangular, and exponential distributions, thereby effectively modeling both inter-grade uncertainty and asymmetry. Experimental results demonstrate that all soft-label strategies significantly outperform baseline methods (p<0.001), achieving quadratic weighted kappa (QWK) scores of 0.777 for KL and 0.796 for CPPD grading, along with notable improvements in mean absolute error (MAE) and other evaluation metrics.

Abstract

Background and objective. Conventional Deep Learning (DL) approaches for Knee Osteoarthritis (KOA) grading rely on one-hot labels, which fail to capture both the ordinal uncertainty of Kellgren--Lawrence (KL) and Calcium Pyrophosphate Deposition Disease (CPPD) severity scores and the asymmetric relationship between the two scales observed in clinical practice. Methods. We retrospectively collected 2172 knee X-ray images, including 968 radiographs jointly annotated for KL and CPPD severity. An ordinal DL framework based on soft-labelling was developed for both tasks, replacing one-hot targets with unimodal probability distributions centred on the annotated grade. Four formulations were investigated: binomial, beta, triangular, and exponential. Results. All soft-labelling strategies consistently outperformed the nominal baseline. For CPPD grading, the triangular formulation achieved the highest Quadratic Weighted Kappa (QWK) and the lowest Mean Absolute Error (MAE) (QWK = 0.796; MAE = 0.438), while the beta formulation yielded the most balanced class-wise performance considering Average MAE (AMAE) and Maximum MAE (MMAE) across classes (AMAE = 0.458; MMAE = 0.573). For KL grading, the beta-based approach provided the best overall performance, achieving the highest QWK together with the lowest MAE and class-wise errors (QWK = 0.777; MAE = 0.529; AMAE = 0.523; MMAE = 0.775). Statistical analysis demonstrated significant improvements over conventional one-hot supervision (p < 0.001).

Problem

• Knee Osteoarthritis
• Kellgren-Lawrence grading
• Calcium Pyrophosphate Deposition Disease
• ordinal uncertainty
• soft labelling

Innovation

• soft-labelling
• ordinal classification
• knee osteoarthritis
• KL grading
• CPPD