Post

New research · Ophthalmology
Graefe's archive for clinical and experimental ophthalmology = Albrecht von Graefes Archiv fur klinische und experimentelle Ophthalmologie · 16h
AI / informaticsGraefe's archive for clinical and experimental ophthalmology = Albrecht von Graefes Archiv fur klinische und experimentelle Ophthalmologie · 2026

Utilizing artificial intelligence for the diagnosis of ocular surface squamous neoplasia with ultrasound biomicroscopy images.

Kubra Serbest Ceylanoglu, Zhao Zhenyang, Bernadete Ayres … Hakan Demirci
Read paper
OphthalmologyAI / informatics

Artificial intelligence model distinguished ocular surface squamous neoplasia from benign lesions on ultrasound imaging

Utilizing artificial intelligence for the diagnosis of ocular surface squamous neoplasia with ultrasound biomicroscopy images.

Kubra Serbest Ceylanoglu … Hakan Demirci
Graefe's archive for clinical and experimental ophthalmology = Albrecht von Graefes Archiv fur klinische und experimentelle Ophthalmologie · 2026
Purpose

This study aims to develop an artificial intelligence (artificial intelligence) model to assist ophthalmologists in distinguishing ocular surface squamous neoplasia (ocular surface squamous neoplasia) from benign ocular surface lesions using ultrasound biomicroscopy (ultrasound biomicroscopy) images.

Methods

Data were retrospectively collected from 139 patients with biopsy-proven conjunctival lesions, including 201 ultrasound biomicroscopy images of benign lesions (e.g.,pterygium, squamous papilloma) and 381 images of ocular surface squamous neoplasia (e.g.,squamous cell carcinoma, conjunctival intraepithelial neoplasia).

n = 381 images
Results
0.83
how well the artificial intelligence told tumor from non-tumor scans apart overall - higher is better
n = 381 images
More results

It significantly outperformed two ocular oncology fellows (p = 0.02 and 0.03, respectively) and demonstrated borderline significance compared to a senior ophthalmologist (p = 0.05).

The heatmaps effectively highlighted the lesions, suggesting that echogenicity played a crucial role in the model's predictions.

More results

None of the patient-related factors significantly affected model performance (all p > 0.1), supporting its equitable diagnostic capability across diverse patient groups.

“
Conclusion · 1 of 2

This study demonstrates the feasibility of using artificial intelligence to differentiate ocular surface squamous neoplasia from benign conjunctival lesions based on ultrasound biomicroscopy images.

Conclusion · 2 of 2

The heatmap enhances model transparency, and the consistent performance across patient subgroups highlights its potential as a fair and valuable tool for clinical decision-making in ocular surface tumor evaluation.

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
0.98
Artificial intelligence's eyelid-height measurements matched doctors' manual measurements almost perfectly
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