Post

New research · Ophthalmology
Ophthalmology science · 11h
AI / informaticsOphthalmology science · 2026

Marker-Free, Automated Eyelid Assessment in Thyroid Eye Disease Using Artificial Intelligence: A Multicenter Validation Study.

Jae Hoon Moon, Jongchan Kim, Joonhyeon Park … Antonio Manuel Garrido Hermosilla
Read paper
OphthalmologyAI / informatics

Artificial intelligence eyelid measurements closely matched ground truth for MRD1 in thyroid eye disease

Marker-Free, Automated Eyelid Assessment in Thyroid Eye Disease Using Artificial Intelligence: A Multicenter Validation Study.

Jae Hoon Moon … Antonio Manuel Garrido Hermosilla
Ophthalmology science · 2026
Purpose

To validate "Glandy LID," a novel marker-free, deep learning-based software designed for the automated assessment of eyelid morphology using intrinsic corneal diameter for calibration.

Methods

The internal validation cohort consisted of 119 patients with thyroid eye disease (thyroid eye disease) from Seoul National University Bundang Hospital (South Korea).

n = 140 patients
0.98
Results
0.98
Artificial intelligence's eyelid-height measurements matched doctors' manual measurements almost perfectly
n = 140 patients
More results

In the internal validation, the artificial intelligence system demonstrated high geometric precision (Intersection over Union 0.94).

In the external validation using smartphone images without markers, the system maintained high reliability.

For MRD1, it achieved a pearson correlation coefficient of 0.94 and a mean absolute percentage error of 9.06%.

More results

Although MRD2 showed a slightly higher mean absolute percentage error (15.07%), likely due to manual measurement variability in clinical records, the correlation remained strong (pearson correlation coefficient 0.93).

“
Conclusion · 1 of 3

This artificial intelligence system provides an accurate and robust automated solution for eyelid measurement without the need for physical reference markers.

Conclusion · 2 of 3

By overcoming the limitations of manual assessment and marker-based systems, this tool offers a practical and accessible method for objectively monitoring thyroid eye disease in both routine clinical practice and remote health care settings.

Conclusion · 3 of 3

FINANCIAL

Read paper
0 comments

No comments yet. Be the first.

Related papers

LatestFoundational
AI / Informatics
0·962 for OCT
MerMED-FM was very accurate at diagnosing diseases using eye scans
AI / Informatics
92.1%
combining eye scans and photos correctly told benign from cancerous lesions apart nearly every time
Cohort Study
28.6%
recurred locally in more than 1 in 4 patients over years of follow-up
Cohort Study
-0.395
excision group's post-op eyelid fullness score was lower - greater improvement
Cohort Study
86.7%
of infants probed after 12 months still had unresolved tear duct blockage
Observational
16%
eyelid tissue in rosacea patients showed less of this key repair-signaling protein inside cell nuclei
Cohort Study
25%
about 1 in 4 treated cases had symptoms return after improving
Cohort Study
6.0% vs. 3.5%
checked complications after surgery, similar with either choice