Original Article
A Deep Learning Network for Classifying Arteries and Veins in Montaged Widefield OCT Angiograms

https://doi.org/10.1016/j.xops.2022.100149Get rights and content
Under a Creative Commons license
open access

Purpose

To propose a deep-learning−based method to differentiate arteries from veins in montaged widefield OCT angiography (OCTA).

Design

Cross-sectional study.

Participants

A total of 232 participants, including 109 participants with diabetic retinopathy (DR), 64 participants with branch retinal vein occlusion (BRVO), 27 participants with diabetes but without DR, and 32 healthy participants.

Methods

We propose a convolutional neural network (CAVnet) to classify retinal blood vessels on montaged widefield OCTA en face images as arteries and veins. A total of 240 retinal angiograms from 88 eyes were used to train CAVnet, and 302 retinal angiograms from 144 eyes were used for testing. This method takes the OCTA images as input and outputs the segmentation results with arteries and veins down to the level of precapillary arterioles and postcapillary venules. The network also identifies their intersections. We evaluated the agreement (in pixels) between segmentation results and the manually graded ground truth using sensitivity, specificity, F1-score, and Intersection over Union (IoU). Measurements of arterial and venous caliber or tortuosity are made on our algorithm’s output of healthy and diseased eyes.

Main Outcome Measures

Classification of arteries and veins, arterial and venous caliber, and arterial and venous tortuosity.

Results

For classification and identification of arteries, the algorithm achieved average sensitivity of 95.3%, specificity of 99.6%, F1 score of 94.2%, and IoU of 89.3%. For veins, the algorithm achieved average sensitivity of 94.4%, specificity of 99.7%, F1 score of 94.1%, and IoU of 89.2%. We also achieved an average sensitivity of 76.3% in identifying intersection points. The results show CAVnet has high accuracy on differentiating arteries and veins in DR and BRVO cases. These classification results are robust across 2 instruments and multiple scan volume sizes. Outputs of CAVnet were used to measure arterial and venous caliber or tortuosity, and pixel-wise caliber and tortuosity maps were generated. Differences between healthy and diseased eyes were demonstrated, indicating potential clinical utility.

Conclusions

The CAVnet can classify arteries and veins and their branches with high accuracy and is potentially useful in the analysis of vessel type-specific features on diseases such as branch retinal artery occlusion and BRVO.

Keywords

Classification of arteries and veins
Deep learning
Measurement of their caliber and tortuosity

Abbreviations and Acronyms

BRVO
branch retinal vein occlusion
CAVnet
classification of artery and vein network
CE
cross-entropy
DR
diabetic retinopathy
IoU
Intersection over Union
NPDR
nonproliferative diabetic retinopathy
OCTA
OCT angiography
PDR
proliferative diabetic retinopathy

Cited by (0)

Supplemental material available at www.ophthalmologyscience.org.

Training Parameters are available at https://github.com/octangio/CAVnet.

Disclosure(s): All authors have completed and submitted the ICMJE disclosures form.

The author(s) have made the following disclosure(s): D.H.: Funding, Consulting, Patent – Optovue; Y.J.: Funding and Patent – Optovue; Patents – Optos. Oregon Health & Science University, Y.J. and D.H. have a financial interest in Optovue, Inc., a company that may have a commercial interest in the results of this research and technology. These potential conflicts of interest have been reviewed and are managed by OHSU.

Funding: National Institutes of Health (R01 EY027833, R01 EY024544, R01 EY031394, P30 EY010572, T32 EY023211); unrestricted departmental funding grant and William & Mary Greve Special Scholar Award from Research to Prevent Blindness (New York, NY); Bright Focus Foundation (G2020168).

HUMAN SUBJECTS: Human subjects were included in this study. The human ethics committees at the Oregon Health & Science University approved the study. All research adhered to the tenets of the Declaration of Helsinki. All participants provided informed consent.

No animal subjects were used in this study.

Author Contributions:

Conception and design: Gao, Jia

Data collection: Gao, Guo, Tsuboi, Pacheco, Poole

Analysis and interpretation: Gao, Guo, Hormel

Obtained funding: Jia, Hwang; Study was performed as part of regular employment duties at Oregon Health & Science University. No additional funding was provided.

Overall responsibility: Gao, Hormel, Bailey, Flaxel, Huang, Hwang, Jia