Utilizing artificial intelligence for the diagnosis of ocular surface squamous neoplasia with ultrasound…

AI / informaticsGraefe's archive for clinical and experimental ophthalmology = Albrecht von Graefes Archiv fur klinische und experimentelle Ophthalmologie· Apr 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

Ocular OncologyAI / informaticsDiagnosisQ1IF 3.1

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 · Apr 2026 · Q1 in Ophthalmology

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.

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

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

Related papers