Background Optical coherence tomography angiography (OCTA) is increasingly being used to evaluate diabetic retinopathy, but the interpretation of OCTA remains largely subjective. The purpose of this study was to design a computer-aided diagnostic (CAD) system to diagnose non-proliferative diabetic retinopathy (NPDR) in an automated fashion using OCTA images.
Methods This was a two-centre, cross-sectional study. Adults with type II diabetes mellitus (DMII) were eligible for inclusion. OCTA scans of the macula were taken, and the five vascular maps generated per eye were analysed by a novel CAD system. For the purpose of classification/diagnosis, three different local features—blood vessel density, blood vessel calibre and the size of the foveal avascular zone (FAZ)—were segmented from these images and used to train a new, automated classifier.
Results One hundred and six patients with DMII were included in the study, 23 with no DR and 83 with mild NPDR. When using features of the superficial retinal map alone, the system demonstrated an accuracy of 80.0% and area under the curve (AUC) of 76.2%. Using the features of the deep retinal map alone, accuracy was 91.4% and AUC 89.2%. When data from both maps were combined, the presented CAD system demonstrated overall accuracy of 94.3%, sensitivity of 97.9%, specificity of 87.0%, area under curve (AUC) of 92.4% and dice similarity coefficient of 95.8%.
Conclusion Automated diagnosis of NPDR using OCTA images is feasible and accurate. Combining this system with OCT data is a plausible next step that would likely improve its robustness.
- diagnostic tests/investigation
Statistics from Altmetric.com
Contributors NE and ME: analysis and interpretation of data, drafted the work and revised it critically for important intellectual content and final approval of the version to be published. OH: collection of data. RK: obtained funding and revised the article critically for important intellectual content and did final approval of the version to be published. SS: conception and design of the study, collection of data, obtained funding for the study, revised the article critically for important intellectual content and did final approval of the version to be published. AE-B: conception and design of the study, the analysis and interpretation of data, obtained funding for the study, revised the article critically for important intellectual content and did final approval of the version to be published. HSS: analysis and interpretation of data, the collection of data, drafting the work, revised it critically for important intellectual content and did final approval of the version to be published, and agreed to be accountable for all aspects of the work in ensuring that questions related to the accuracy or integrity of any part of the work are appropriately investigated and resolved.
Funding This work was supported in part by Research to Prevent Blindness grant number RPB-1944.
Competing interests None declared.
Ethics approval Institutional Review Boards of the University of Louisville and the University of Massachusetts.
Provenance and peer review Not commissioned; externally peer reviewed.
Data sharing statement De-identified patient demographic information and limited clinical information can be made available upon request. The technical transformations involved in the machine learning analysis take a large amount of data and is difficult to transfer, but parts of it can be made available upon request.
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.