In Vivo Classification of Patellar Motion Trajectories in Individuals: A 4D-CT-Based Study with Unsupervised Clustering.

Background

Patellar motion trajectory (PMT) is a key kinematic parameter for evaluating patellofemoral joint (PFJ) stability, but traditional static imaging indices are unable to capture the dynamic six-degrees-of-freedom (6-DOF) characteristics of patellar motion throughout the entire knee flexion-extension cycle. Four-dimensional computed tomography (4D-CT) facilitates in vivo dynamic imaging of the PFJ, while the systematic classification of PMT in asymptomatic populations has remained underexplored.

Methods

A retrospective cross-sectional study was performed on 64 asymptomatic and functionally normal knees that underwent 4D-CT dynamic scanning from March 2021 to December 2025. Patellar 6-DOF kinematic data during 0° to 90° of knee flexion-extension were extracted through manifold optimization, automatic segmentation, and spatial registration. Following standardization of the motion cycle, unsupervised K-means clustering was employed to classify PMT phenotypes, with nonparametric tests used to analyze intergroup kinematic differences and evaluate clustering quality.

Results

Three distinct PMT types were identified based on clustering validity indices, including a silhouette score of 0.381, a Davies-Bouldin index of 0.916, and a Calinski-Harabasz index of 44.06: Type 1 (7.81%, 35.11 ± 6.56 mm), Type 2 (56.25%, 15.67 ± 6.59 mm), and Type 3 (35.94%, 2.82 ± 2.41 mm). Lateral translation (Tx) served as the dominant determinant for PMT typing (p < 0.001), whereas non-lateral DOF parameters exhibited no consistent intergroup differences. Postural DOFs exhibited coupled fluctuations with Tx but had no independent stratification effect. Traditional static imaging parameters demonstrated no consistent correlation with these dynamic subtypes.

Conclusions

Functionally asymptomatic knees exhibited three in vivo patellar 6-DOF motion trajectory phenotypes dominated by lateral translation amplitude. This 4D-CT-based typing framework provides a dynamic kinematic baseline for PFJ stability evaluation and lays a foundation for individualized optimization of ligament reconstruction and pathophysiological research of patellofemoral disorders.