An Open-Source Deep Learning Network for Reconstruction of High-Resolution OCT Angiograms of Retinal Intermediate and Deep Capillary Plexuses

Overview

Journal Transl Vis Sci Technol

Specialties Biomedical Engineering
Ophthalmology

Date 2021 Nov 10

PMID 34757393

Citations 11

Authors

Min Gao

Tristan T Hormel

Jie Wang

Yukun Guo

Steven T Bailey

Thomas S Hwang

Yali Jia

Affiliations

Soon will be listed here.

Abstract

Purpose: We propose a deep learning-based image reconstruction algorithm to produce high-resolution optical coherence tomographic angiograms (OCTA) of the intermediate capillary plexus (ICP) and deep capillary plexus (DCP).

Methods: In this study, 6-mm × 6-mm macular scans with a 400 × 400 A-line sampling density and 3-mm × 3-mm scans with a 304 × 304 A-line sampling density were acquired on one or both eyes of 180 participants (including 230 eyes with diabetic retinopathy and 44 healthy controls) using a 70-kHz commercial OCT system (RTVue-XR; Optovue, Inc., Fremont, California, USA). Projection-resolved OCTA algorithm removed projection artifacts in voxel. ICP and DCP angiograms were generated by maximum projection of the OCTA signal within the respective plexus. We proposed a deep learning-based method, which receives inputs from registered 3-mm × 3-mm ICP and DCP angiograms with proper sampling density as the ground truth reference to reconstruct 6-mm × 6-mm high-resolution ICP and DCP en face OCTA. We applied the same network on 3-mm × 3-mm angiograms to enhance these images further. We evaluated the reconstructed 3-mm × 3-mm and 6-mm × 6-mm angiograms based on vascular connectivity, Weber contrast, false flow signal (flow signal erroneously generated from background), and the noise intensity in the foveal avascular zone.

Results: Compared to the originals, the Deep Capillary Angiogram Reconstruction Network (DCARnet)-enhanced 6-mm × 6-mm angiograms had significantly reduced noise intensity (ICP, 7.38 ± 25.22, P < 0.001; DCP, 11.20 ± 22.52, P < 0.001), improved vascular connectivity (ICP, 0.95 ± 0.01, P < 0.001; DCP, 0.96 ± 0.01, P < 0.001), and enhanced Weber contrast (ICP, 4.25 ± 0.10, P < 0.001; DCP, 3.84 ± 0.84, P < 0.001), without generating false flow signal when noise intensity lower than 650. The DCARnet-enhanced 3-mm × 3-mm angiograms also reduced noise, improved connectivity, and enhanced Weber contrast in 3-mm × 3-mm ICP and DCP angiograms from 101 eyes. In addition, DCARnet preserved the appearance of the dilated vessels in the reconstructed angiograms in diabetic eyes.

Conclusions: DCARnet can enhance 3-mm × 3-mm and 6-mm × 6-mm ICP and DCP angiogram image quality without introducing artifacts.

Translational Relevance: The enhanced 6-mm × 6-mm angiograms may be easier for clinicians to interpret qualitatively.

Citing Articles

Advances in OCT Angiography.

Hormel T, Huang D, Jia Y Transl Vis Sci Technol. 2025; 14(3):6.

PMID: 40052848 PMC: 11905608. DOI: 10.1167/tvst.14.3.6.

Automated Imaging of Cataract Surgery Using Artificial Intelligence.

Kim Y, Hwang S, Kim K, Nam D Diagnostics (Basel). 2025; 15(4).

PMID: 40002596 PMC: 11854092. DOI: 10.3390/diagnostics15040445.

AI-based 3D analysis of retinal vasculature associated with retinal diseases using OCT angiography.

Liu Y, Tang Z, Li C, Zhang Z, Zhang Y, Wang X Biomed Opt Express. 2024; 15(11):6416-6432.

PMID: 39553857 PMC: 11563331. DOI: 10.1364/BOE.534703.

Enhanced microvascular imaging through deep learning-driven OCTA reconstruction with squeeze-and-excitation block integration.

Rashidi M, Kalenkov G, Green D, McLaughlin R Biomed Opt Express. 2024; 15(10):5592-5608.

PMID: 39421773 PMC: 11482165. DOI: 10.1364/BOE.525928.

Multi-Plexus Nonperfusion Area Segmentation in Widefield OCT Angiography Using a Deep Convolutional Neural Network.

Guo Y, Hormel T, Gao M, You Q, Wang J, Flaxel C Transl Vis Sci Technol. 2024; 13(7):15.

PMID: 39023443 PMC: 11262538. DOI: 10.1167/tvst.13.7.15.

References

Sjolie A, Klein R, Porta M, Orchard T, Fuller J, Parving H . Retinal microaneurysm count predicts progression and regression of diabetic retinopathy. Post-hoc results from the DIRECT Programme. Diabet Med. 2011; 28(3):345-51. DOI: 10.1111/j.1464-5491.2010.03210.x. View

Camino A, Jia Y, Liu G, Wang J, Huang D . Regression-based algorithm for bulk motion subtraction in optical coherence tomography angiography. Biomed Opt Express. 2017; 8(6):3053-3066. PMC: 5480449. DOI: 10.1364/BOE.8.003053. View

Jiang Z, Huang Z, Qiu B, Meng X, You Y, Liu X . Comparative study of deep learning models for optical coherence tomography angiography. Biomed Opt Express. 2020; 11(3):1580-1597. PMC: 7075619. DOI: 10.1364/BOE.387807. View

Soares J, Leandro J, Cesar Junior R, Jelinek H, Cree M . Retinal vessel segmentation using the 2-D Gabor wavelet and supervised classification. IEEE Trans Med Imaging. 2006; 25(9):1214-22. DOI: 10.1109/tmi.2006.879967. View

Kumar A, Kim J, Lyndon D, Fulham M, Feng D . An Ensemble of Fine-Tuned Convolutional Neural Networks for Medical Image Classification. IEEE J Biomed Health Inform. 2017; 21(1):31-40. DOI: 10.1109/JBHI.2016.2635663. View

Chlebiej M, Gorczynska I, Rutkowski A, Kluczewski J, Grzona T, Pijewska E . Quality improvement of OCT angiograms with elliptical directional filtering. Biomed Opt Express. 2019; 10(2):1013-1031. PMC: 6377873. DOI: 10.1364/BOE.10.001013. View

Hormel T, Jia Y, Jian Y, Hwang T, Bailey S, Pennesi M . Plexus-specific retinal vascular anatomy and pathologies as seen by projection-resolved optical coherence tomographic angiography. Prog Retin Eye Res. 2020; 80:100878. PMC: 7855241. DOI: 10.1016/j.preteyeres.2020.100878. View

Hwang T, Gao S, Liu L, Lauer A, Bailey S, Flaxel C . Automated Quantification of Capillary Nonperfusion Using Optical Coherence Tomography Angiography in Diabetic Retinopathy. JAMA Ophthalmol. 2016; 134(4):367-73. PMC: 4978127. DOI: 10.1001/jamaophthalmol.2015.5658. View

Wei X, Hormel T, Guo Y, Hwang T, Jia Y . High-resolution wide-field OCT angiography with a self-navigation method to correct microsaccades and blinks. Biomed Opt Express. 2020; 11(6):3234-3245. PMC: 7316026. DOI: 10.1364/BOE.390430. View

10.

Hormel T, Wang J, Bailey S, Hwang T, Huang D, Jia Y . Maximum value projection produces better OCT angiograms than mean value projection. Biomed Opt Express. 2019; 9(12):6412-6424. PMC: 6491019. DOI: 10.1364/BOE.9.006412. View

11.

Jia Y, Tan O, Tokayer J, Potsaid B, Wang Y, Liu J . Split-spectrum amplitude-decorrelation angiography with optical coherence tomography. Opt Express. 2012; 20(4):4710-25. PMC: 3381646. DOI: 10.1364/OE.20.004710. View

12.

Hwang T, Jia Y, Gao S, Bailey S, Lauer A, Flaxel C . OPTICAL COHERENCE TOMOGRAPHY ANGIOGRAPHY FEATURES OF DIABETIC RETINOPATHY. Retina. 2015; 35(11):2371-6. PMC: 4623938. DOI: 10.1097/IAE.0000000000000716. View

13.

Hormel T, Huang D, Jia Y . Artifacts and artifact removal in optical coherence tomographic angiography. Quant Imaging Med Surg. 2021; 11(3):1120-1133. PMC: 7829161. DOI: 10.21037/qims-20-730. View

14.

Falavarjani K, Al-Sheikh M, Akil H, Sadda S . Image artefacts in swept-source optical coherence tomography angiography. Br J Ophthalmol. 2016; 101(5):564-568. DOI: 10.1136/bjophthalmol-2016-309104. View

15.

Gao M, Guo Y, Hormel T, Sun J, Hwang T, Jia Y . Reconstruction of high-resolution 6×6-mm OCT angiograms using deep learning. Biomed Opt Express. 2020; 11(7):3585-3600. PMC: 7510902. DOI: 10.1364/BOE.394301. View

16.

Say E, Ferenczy S, Magrath G, Samara W, Khoo C, Shields C . IMAGE QUALITY AND ARTIFACTS ON OPTICAL COHERENCE TOMOGRAPHY ANGIOGRAPHY: Comparison of Pathologic and Paired Fellow Eyes in 65 Patients With Unilateral Choroidal Melanoma Treated With Plaque Radiotherapy. Retina. 2016; 37(9):1660-1673. DOI: 10.1097/IAE.0000000000001414. View

17.

Wang J, Zhang M, Hwang T, Bailey S, Huang D, Wilson D . Reflectance-based projection-resolved optical coherence tomography angiography [Invited]. Biomed Opt Express. 2017; 8(3):1536-1548. PMC: 5480563. DOI: 10.1364/BOE.8.001536. View

18.

Jia Y, Bailey S, Hwang T, McClintic S, Gao S, Pennesi M . Quantitative optical coherence tomography angiography of vascular abnormalities in the living human eye. Proc Natl Acad Sci U S A. 2015; 112(18):E2395-402. PMC: 4426471. DOI: 10.1073/pnas.1500185112. View

19.

Guo Y, Hormel T, Gao L, You Q, Wang B, Flaxel C . Quantification of Nonperfusion Area in Montaged Widefield OCT Angiography Using Deep Learning in Diabetic Retinopathy. Ophthalmol Sci. 2022; 1(2):100027. PMC: 9560579. DOI: 10.1016/j.xops.2021.100027. View

20.

Guo Y, Camino A, Wang J, Huang D, Hwang T, Jia Y . MEDnet, a neural network for automated detection of avascular area in OCT angiography. Biomed Opt Express. 2018; 9(11):5147-5158. PMC: 6238913. DOI: 10.1364/BOE.9.005147. View