Automated diabetic retinopathy detection using optical coherence tomography angiography: a pilot study. Issue 11 (23rd January 2018)

• Record Type: Journal Article
• Authors: Sandhu, Harpal Singh; Eladawi, Nabila; Elmogy, Mohammed; Keynton, Robert; Helmy, Omar; Schaal, Shlomit; El-Baz, Ayman
• Is Part Of: British journal of ophthalmology. Volume 102:Issue 11(2018)
• Page Start: 1564
• Page End: 1569
• Publication Date: 2018-01-23
• Subjects: retina -- imaging -- diagnostic tests/investigation; Ophthalmology -- Periodicals; 617.7
• DOI: 10.1136/bjophthalmol-2017-311489
• Languages: English
• ISSNs: 0007-1161

Abstract

Abstract : 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.