Related Experiment Video
Updated: May 5, 2026
Integrated Photoacoustic Ophthalmoscopy and Spectral-domain Optical Coherence Tomography
Published on: January 15, 2013
Detection of Ocular Surface Squamous Neoplasia Using Artificial Intelligence With Anterior Segment Optical Coherence
Jason A Greenfield1, Rafael Scherer1, Diego Alba1
1From the Bascom Palmer Eye Institute (J.A.G., R.S., D.A., S.D.A., O.A., S.P., D.R.C., W.H., M.A., A.J., H.A.K., W.W., M.A.S., R.O., A.G., F.A.M., C.L.K.), University of Miami Miller School of Medicine, Miami, Florida, USA.
Purpose:
To develop and validate a deep learning (DL) model to differentiate ocular surface squamous neoplasia (OSSN) from pterygium and pinguecula using high-resolution anterior segment optical coherence tomography (AS-OCT).
Design:
Retrospective Diagnostic Accuracy Study.
Methods:
Setting: Single-center.
Study Population:
All eyes with a clinical or biopsy-proven diagnosis of OSSN, pterygium, or pinguecula that received AS-OCT imaging.
Procedures:
Imaging data was extracted from Optovue AS-OCT (Fremont, CA) and patients' clinical or biopsy-proven diagnoses were collected from electronic medical records. A DL classification model was developed using two methodologies: (1) a masked autoencoder was trained with unlabeled data from 105,859 AS-OCT images of 5746 eyes and (2) a Vision Transformer supervised model coupled to the autoencoder used labeled data for fine-tuning a binary classifier (OSSN vs non-OSSN lesions). A sample of 2022 AS-OCT images from 523 eyes (427 patients) were classified by expert graders into "OSSN or suspicious for OSSN" and "pterygium or pinguecula." The algorithm's diagnostic performance was evaluated in a separate test sample using 566 scans (62 eyes, 48 patients) with biopsy-proven OSSN and compared with expert clinicians who were masked to the diagnosis. Analysis was conducted at the scan-level for both the DL model and expert clinicians, who were not provided with clinical images or supporting clinical data.
Main Outcome:
Diagnostic performance of expert clinicians and the DL model in identifying OSSN on AS-OCT scans.
Results:
The DL model had an accuracy of 90.3% (95% confidence intervals [CI]: 87.5%-92.6%), with sensitivity of 86.4% (95% CI: 81.4%-90.4%) and specificity of 93.2% (95% CI: 89.9%-95.7%) compared to the biopsy-proven diagnosis. Expert graders had a lower sensitivity 69.8% (95% CI: 63.6%-75.5%) and slightly higher specificity 98.5% (95% CI: 96.4%-99.5%) than the DL model. The area under the receiver operating characteristic curve for the DL model was 0.945 (95% CI: 0.918-0.972) and significantly greater than expert graders (area under the receiver operating characteristic curve = 0.688, P < .001).
Conclusions:
A DL model applied to AS-OCT scans demonstrated high accuracy, sensitivity, and specificity in differentiating OSSN from pterygium and pinguecula. Interestingly, the model had comparable diagnostic performance to expert clinicians in this study and shows promise for enhancing clinical decision-making. Further research is warranted to explore the integration of this artificial intelligence-driven approach in routine screening and diagnostic protocols for OSSN.
