Implementing automated 3D measurements to quantify reference values and side-to-side differences in the ankle...

Detection of syndesmotic ankle instability remains challenging in clinical practice due to the limitations of two-dimensional (2D) measurements. The transition to automated three-dimensional (3D) measurement techniques is on the verge of a breakthrough but normative and side-to-side comparative data are missing. Therefore, our study aim was two-fold: (1) to establish 3D anatomical reference values of the ankle syndesmosis based on automated measurements and (2) to determine to what extent the ankle syndesmosis is symmetric across all 3D measurements. Patients without syndesmotic pathology with a non-weight-bearing CT scan (NWBCT; N = 38; Age = 51.6 ± 17.43 years) and weight-bearing CT scan (WBCT; N = 43; Age = 48.9 ± 14.3 years) were retrospectively included. After training and validation of a neural network to automate the segmentation of 3D ankle models, an iterative closest point registration was performed to superimpose the left on the right ankle. Subsequently, 3D measurements were manually and automatically computed using a custom-made algorithm and side-to-side comparison of these landmarks allowed one to investigate symmetry. Intra-observer analysis showed excellent agreements for all manual measurements (ICC range 0.85-0.99) and good (i.e. < 2.7° for the angles and < 0.5 mm for the distances) accuracy was found between the automated and manual measurements. A mean Dice coefficient of 0.99 was found for the automated segmentation framework. The established mean, standard deviation and range were provided for each 3D measurement. From these data, reference values were derived to differ physiological from pathological syndesmotic alignment. Furthermore, side-to-side symmetry was revealed when comparing left to right measurements (P > 0.05). In clinical practice, our novel algorithm could surmount the current limitations of manual 2D measurements and distinguish patients with a syndesmotic ankle lesion from normal variance.