Automated Detection of Posterior Vitreous Detachment on OCT Using Computer Vision and Deep Learning Algorithms

Alexa L Li; Moira Feng; Zixi Wang; Sally L Baxter; Lingling Huang; Justin Arnett; Dirk-Uwe G Bartsch; David E Kuo; Bharanidharan Radha Saseendrakumar; Joy Guo; Eric Nudleman

doi:10.1016/j.xops.2022.100254

Automated Detection of Posterior Vitreous Detachment on OCT Using Computer Vision and Deep Learning Algorithms

Ophthalmol Sci. 2022 Nov 11;3(2):100254. doi: 10.1016/j.xops.2022.100254. eCollection 2023 Jun.

Authors

Alexa L Li¹, Moira Feng², Zixi Wang², Sally L Baxter^{1

3}, Lingling Huang¹, Justin Arnett¹, Dirk-Uwe G Bartsch¹, David E Kuo¹, Bharanidharan Radha Saseendrakumar^{1

3}, Joy Guo^{1

3}, Eric Nudleman¹

Affiliations

¹ Viterbi Family Department of Ophthalmology and Shiley Eye Institute, University of California at San Diego, La Jolla, California.
² Jacobs School of Engineering, University of California San Diego, La Jolla, California.
³ Health Department of Biomedical Informatics, University of California San Diego, La Jolla, California.

Abstract

Objective: To develop automated algorithms for the detection of posterior vitreous detachment (PVD) using OCT imaging.

Design: Evaluation of a diagnostic test or technology.

Subjects: Overall, 42 385 consecutive OCT images (865 volumetric OCT scans) obtained with Heidelberg Spectralis from 865 eyes from 464 patients at an academic retina clinic between October 2020 and December 2021 were retrospectively reviewed.

Methods: We developed a customized computer vision algorithm based on image filtering and edge detection to detect the posterior vitreous cortex for the determination of PVD status. A second deep learning (DL) image classification model based on convolutional neural networks and ResNet-50 architecture was also trained to identify PVD status from OCT images. The training dataset consisted of 674 OCT volume scans (33 026 OCT images), while the validation testing set consisted of 73 OCT volume scans (3577 OCT images). Overall, 118 OCT volume scans (5782 OCT images) were used as a separate external testing dataset.

Main outcome measures: Accuracy, sensitivity, specificity, F1-scores, and area under the receiver operator characteristic curves (AUROCs) were measured to assess the performance of the automated algorithms.

Results: Both the customized computer vision algorithm and DL model results were largely in agreement with the PVD status labeled by trained graders. The DL approach achieved an accuracy of 90.7% and an F1-score of 0.932 with a sensitivity of 100% and a specificity of 74.5% for PVD detection from an OCT volume scan. The AUROC was 89% at the image level and 96% at the volume level for the DL model. The customized computer vision algorithm attained an accuracy of 89.5% and an F1-score of 0.912 with a sensitivity of 91.9% and a specificity of 86.1% on the same task.

Conclusions: Both the computer vision algorithm and the DL model applied on OCT imaging enabled reliable detection of PVD status, demonstrating the potential for OCT-based automated PVD status classification to assist with vitreoretinal surgical planning.

Financial disclosures: Proprietary or commercial disclosure may be found after the references.

Keywords: AI, artificial intelligence; AUROC, area under the receiver operator characteristic curve; Automated detection; CNN, convolutional neural network; DL, deep learning; Deep Learning; ILM, internal limiting membrane; OCT; PVD, posterior vitreous detachment; Posterior vitreous detachment; ViT, vision transformers.