<- Back to digest

JSES - 2026-04-09 - Journal Article

The Effect of Glenoid Rotational Malalignment on Best-Fit Circles Based on AI-Generated Mathematically True Glenoid En-Face Views.

Assiotis A, Rumian A, Guilliatt M, Andrews T, Soogumbur A, Uppal HS

retrospective cohortLOE IIIn = 40N/A

Topics

arthroplastyshoulder elbowsports
PMID: 41966471DOI: 10.1016/j.jse.2026.03.024View on PubMed ->

Key Takeaway

Glenoid rotation of as little as 5 degrees from the mathematically true en-face view produces statistically significant errors in best-fit circle diameter, position, and calculated bone loss percentage in AI-generated CT reconstructions of 40 instability patients.

Summary Depth

Choose how much analysis to show on this article page.

Summary

This study asked whether rotational malalignment of the glenoid en-face view affects bone loss quantification used in instability planning. Using a custom deep learning platform on CT scans of 40 anterior instability patients, the authors generated mathematically true en-face views and then systematically rotated the glenoid around vertical, horizontal, and combined axes in increments including 5 degrees. Rotations as small as 5 degrees produced statistically significant changes in best-fit circle diameter, best-fit circle position, and measured bone loss percentage.

Key Limitation

The study does not validate the AI-generated mathematically true en-face view against a ground-truth reference standard (e.g., intraoperative direct measurement or 3D-printed model), so the accuracy of the reference position itself remains unconfirmed.

Original Abstract

BACKGROUND

The majority of studies that measure glenoid bone loss in the context of shoulder instability, are based on a sagittal image, termed the 'en-face' view, with the aid of best-fit circles. The en-face view has never been standardised in the past. We created a mathematical en-face view of the glenoid and demonstrated the effect that rotation of the glenoid has on best-fit circle size and position.

METHODS

We used a custom deep learning platform, to create a mathematically 'perfect' en-face view using CT scans of 40 patients with anterior shoulder instability. We retrospectively measured the effect of rotating the glenoid around the vertical and horizontal axes, and all combined positions, on measured bone loss, best-fit circle diameter and position.

RESULTS

Rotation of the glenoid en-face view by as little as 5 degrees, may result to a statistically significant effect on bone loss, on the diameter of the best-fit circle and on the position of the best-fit circle.

DISCUSSION

We described a reproducible and mathematically 'perfect' en-face view, not previously described with manual or semi-automated segmentation methods. We demonstrated how small degrees of rotation from that position, may affect the best-fit circle and subsequently the calculated size of the glenoid defect and the glenoid track determination. This underpins the necessity of an accurate establishment of the en-face view, before positioning the best-fit circle. Using a programmatically true en-face view has the potential to increase the precision of measurement of glenoid bone loss.