Skip to content

Generalisation of a deep learning-based exophthalmometry system using facial photographs for non-thyroidal orbital disease.

Sep 2026 · British Journal of Ophthalmology · pp. bjo-2026-330182 · 0 citations · 27 references
Medicine

TL;DR

The TED-trained photoexophthalmometry system showed good agreement with Hertel measurements in healthy individuals and patients with non-TED orbital disease, and these findings support its use as an adjunct to clinical examination for objective quantification and documentation of globe position.

Abstract

Aims

To evaluate agreement between photo-based automated exophthalmometry and manual Hertel exophthalmometry in healthy individuals and patients with non-thyroidal orbital disease, with a deep learning system trained exclusively in thyroid eye disease (TED) cohorts applied without retraining or fine-tuning.

Methods

This was a retrospective observational study. A total of 269 individuals were included in the study, including 95 healthy controls and 174 patients with unilateral non-TED orbital pathology. Automated measurements obtained using Glandy EXO from same-day frontal facial photographs were compared with corresponding manual Hertel exophthalmometry measurements. Agreement was assessed using Pearson correlation coefficient (PCC), mean absolute error (MAE), intraclass correlation coefficient (ICC) and Bland-Altman analysis. Diagnostic performance for clinically significant intereye asymmetry (>2.0 mm) was also evaluated.

Results

The system showed good agreement with Hertel exophthalmometry in the eyes of healthy controls (PCC 0.80; MAE 0.86 mm; ICC 0.80) as well as the affected (PCC 0.81; MAE 1.41 mm; ICC 0.75) and fellow (PCC 0.76; MAE 1.03 mm; ICC 0.75) eyes of patients. Overall, 84.8% of measurements were within 2.0 mm of the manual Hertel values. The sensitivity, specificity and accuracy of the system for detecting clinically significant intereye asymmetry were 59.6%, 95.0% and 83.3%, respectively.

Conclusions

The TED-trained photoexophthalmometry system showed good agreement with Hertel measurements in healthy individuals and patients with non-TED orbital disease. These findings support its use as an adjunct to clinical examination for objective quantification and documentation of globe position.

View source

Similar papers

Oct 2026

Smartphone-Based Deep Learning Exophthalmometry in Thyroid Eye Disease: A Multicenter, Multiethnic Validation Study.

BACKGROUND Proptosis is the principal quantitative measure of disease severity in thyroid eye disease (TED), but Hertel exophthalmometry has substantial interobserver variability and requires in-person specialist visits. Existing deep learning (DL) proptosis-from-photograph models require studio-acquired images. We aim...

Jae Hoon Moon, Joonhyeon Park, Min Joo Kim et al. · 0 citations
Open access Sep 2026

Smartphone-Based 3D Ocular Reconstruction for Automated Quantitative Blepharoptosis Evaluation.

Importance External ocular examination is central to ptosis evaluation, yet it often relies on manual, experience-dependent measurements with variable accuracy and reproducibility. Objective To develop and prospectively evaluate the Digital Rulers of Ptosis (DRP), a smartphone-based 3-dimensional (3D) reconstruction...

Ya-Han Yang, Yuxuan Han, Rui-Xin Wang et al. · 0 citations
Open access Sep 2026

Automated measurement of Little’s Irregularity Index on intraoral photographs using a convolutional neural network

Quantification of dental irregularities is essential for assessing case severity, evaluating treatment outcomes, and aiding early detection of fixed retainer failure. Measurements are typically performed on casts or digital scans, although manual measurement on intraoral photographs has been explored to enable remote m...

Moritz Kanemeier, Tuna Ergün, Thomas Stamm et al. · 0 citations
Open access Sep 2026

Hospital-Based Reference Values for Hertel Exophthalmometry in Nepal

Background Population-specific reference values for Hertel exophthalmometry are limited in South Asian populations, including Nepal. This limits clinical interpretation of ocular protrusion in routine practice. This study aimed to establish hospital-based reference values for exophthalmometry, evaluate intra-session me...

A. Subedi, Roshni Malla, Mario Cantó-Cerdán et al. · 0 citations
Open access Oct 2026

Interocular symmetry of ocular rigidity and related ocular parameters in isometropia.

PURPOSE Driven by scleral stiffness, ocular rigidity (OR) is emerging as a critical factor in refractive development. Although a common assumption is that OR is symmetric in a healthy individual's eyes, empirical data remains scarce. This study directly tests this assumption by quantifying intereye OR differences in he...

Jonathan Medina-Cornejo, Kelly Lam, Yasaman Adel et al. · 0 citations
Open access Sep 2026

Artificial Intelligence-Powered Craniofacial Photogrammetry Analysis of Pediatric Obstructive Sleep Apnea.

OBJECTIVES To develop an artificial intelligence (AI) system for craniofacial morphology analysis in pediatric obstructive sleep apnea (OSA) using photogrammetry. STUDY DESIGN Prospective, cross-sectional study. SETTING Tertiary medical hospital. METHODS Children aged 3 to 18 years with OSA-related symptoms were...

Wan-Yi Hsueh, Kun-Tai Kang, Shih-Hsu Huang et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.