Synopsis A deep-learning-based macular extrafoveal avascular area (EAA) on a 6×6 mm optical coherence tomography (OCT) angiogram is less dependent on the signal strength and shadow artefacts, providing better diagnostic accuracy for diabetic retinopathy (DR) severity than the commercial software measured extrafoveal vessel density (EVD).
Aims To compare a deep-learning-based EAA to commercial output EVD in the diagnostic accuracy of determining DR severity levels from 6×6 mm OCT angiography (OCTA) scans.
Methods The 6×6 mm macular OCTA scans were acquired on one eye of each participant with a spectral-domain OCTA system. After excluding the central 1 mm diameter circle, the EAA on superficial vascular complex was measured with a deep-learning-based algorithm, and the EVD was obtained with commercial software.
Results The study included 34 healthy controls and 118 diabetic patients. EAA and EVD were highly correlated with DR severity (ρ=0.812 and −0.577, respectively, both p<0.001) and visual acuity (r=−0.357 and 0.420, respectively, both p<0.001). EAA had a significantly (p<0.001) higher correlation with DR severity than EVD. With the specificity at 95%, the sensitivities of EAA for differentiating diabetes mellitus (DM), DR and severe DR from control were 80.5%, 92.0% and 100.0%, respectively, significantly higher than those of EVD 11.9% (p=0.001), 13.6% (p<0.001) and 15.8% (p<0.001), respectively. EVD was significantly correlated with signal strength index (SSI) (r=0.607, p<0.001) and shadow area (r=−0.530, p<0.001), but EAA was not (r=−0.044, p=0.805 and r=−0.046, p=0.796, respectively). Adjustment of EVD with SSI and shadow area lowered sensitivities for detection of DM, DR and severe DR.
Conclusion Macular EAA on 6×6 mm OCTA measured with a deep learning-based algorithm is less dependent on the signal strength and shadow artefacts, and provides better diagnostic accuracy for DR severity than EVD measured with the instrument-embedded software.
Data availability statement
Data are available upon reasonable request. All data relevant to the study are included in the article or uploaded as supplementary information.
Statistics from Altmetric.com
If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.
Contributors Concept and design: HX, QY, YJ. Acquisition, analysis, or interpretation of data: HX, QY, YG, BW, JW, CJF, STB, TSH. Drafting of the manuscript: HX, QY, YJ. Critical revision of the manuscript for important intellectual content: all authors. Statistical analysis: HX, QY. Administrative, technical or material support: YJ, JW, BW, YG. Supervision: YJ. YJ had full access to all the data in the study and takes responsibility for the integrity of the data and the accuracy of the data analysis.
Funding The study was supported by grants R01 EY027833, R01 EY024544 and P30 EY010572 from the National Institutes of Health, an unrestricted departmental funding grant, and William & Mary Greve Special Scholar Award from Research to Prevent Blindness, New York. The sponsor or funding organisation had no role in the design, conduct or submission of this research.
Competing interests YJ and STB (financial support) have a significant financial interest in Optovue Inc. These potential conflicts of interest have been reviewed and are managed by OHSU. The other authors do not have any potential financial conflicts of interest.
Provenance and peer review Not commissioned; externally peer reviewed.