Automated Detection of Central Retinal Artery Occlusion Using OCT Imaging via Explainable Deep Learning

Ansgar Beuse; Daniel Alexander Wenzel; Martin Stephan Spitzer; Karl Ulrich Bartz-Schmidt; Maximilian Schultheiss; Sven Poli; Carsten Grohmann

doi:10.1016/j.xops.2024.100630

Automated Detection of Central Retinal Artery Occlusion Using OCT Imaging via Explainable Deep Learning

Ophthalmol Sci. 2024 Oct 16;5(2):100630. doi: 10.1016/j.xops.2024.100630. eCollection 2025 Mar-Apr.

Authors

Ansgar Beuse¹, Daniel Alexander Wenzel², Martin Stephan Spitzer¹, Karl Ulrich Bartz-Schmidt², Maximilian Schultheiss¹, Sven Poli^{3

4}, Carsten Grohmann¹

Affiliations

¹ Department of Ophthalmology, University Medical Center Hamburg-Eppendorf, Hamburg, Germany.
² University Eye Hospital, Centre for Ophthalmology, University Hospital Tübingen, Tübingen, Germany.
³ Department of Neurology and Stroke, University Hospital Tübingen, Tübingen, Germany.
⁴ Hertie Institute for Clinical Brain Research, University Hospital Tübingen, Tübingen, Germany.

Abstract

Objective: To demonstrate the capability of a deep learning model to detect central retinal artery occlusion (CRAO), a retinal pathology with significant clinical urgency, using OCT data.

Design: Retrospective, external validation study analyzing OCT and clinical baseline data of 2 institutions via deep learning classification analysis.

Subjects: Patients presenting to the University Medical Center Tübingen and the University Medical Center Hamburg-Eppendorf in Germany.

Methods: OCT data of patients suffering from CRAO, differential diagnosis with (sub) acute visual loss (central retinal vein occlusion, diabetic macular edema, nonarteritic ischemic optic neuropathy), and from controls were expertly graded and distinguished into 3 groups. Our methodological approach involved a nested multiclass five fold cross-validation classification scheme.

Main outcome measures: Area under the curve (AUC).

Results: The optimal performance of our algorithm was observed using 30 epochs, complemented by an early stopping mechanism to prevent overfitting. Our model followed a multiclass approach, distinguishing among the 3 different classes: control, CRAO, and differential diagnoses. The evaluation was conducted by the "one vs. all" area under the receiver operating characteristics curve (AUC) method. The results demonstrated AUC of 0.96 (95% confidence interval [CI], ± 0.01); 0.99 (95% CI, ± 0.00); and 0.90 (95% CI, ± 0.03) for each class, respectively.

Conclusions: Our machine learning algorithm (MLA) exhibited a high AUC, as well as sensitivity and specificity in detecting CRAO and the differential classes, respectively. These findings underscore the potential for deploying MLAs in the identification of less common etiologies within an acute emergency clinical setting.

Financial disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Keywords: AI OCT; CRAO; Deep learning retina; OCT imaging; Ophthalmology deep learning.