Vascular changes precede tomographic changes in diabetic eyes without retinopathy and improve artificial intelligence diagnostics. Issue 9 (18th June 2020)

• Record Type: Journal Article
• Authors: Govindaswamy, Nivedhitha; Ratra, Dhanashree; Dalan, Daleena; Doralli, Subashchandra; Tirumalai, Anirudha A.; Nagarajan, Rajesh; Mochi, Thirumalesh; Shetty, Naren; Sinha Roy, Abhijit
• Is Part Of: Journal of biophotonics. Volume 13:Issue 9(2020)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2020-06-18
• Subjects: angiography -- artificial intelligence -- diabetic retinopathy -- optical coherence tomography; Photonics -- Periodicals; Optical materials -- Periodicals; Optics -- Periodicals; Medical instruments and apparatus -- Periodicals; 621.3605
• DOI: 10.1002/jbio.202000107
• Languages: English
• ISSNs: 1864-063X

Abstract

Abstract: The purpose of this study was to evaluate early vascular and tomographic changes in the retina of diabetic patients using artificial intelligence (AI). The study included 74 age‐matched normal eyes, 171 diabetic eyes without retinopathy (DWR) eyes and 69 mild non‐proliferative diabetic retinopathy (NPDR) eyes. All patients underwent optical coherence tomography angiography (OCTA) imaging. Tomographic features (thickness and volume) were derived from the OCTA B‐scans. These features were used in AI models. Both OCT and OCTA features showed significant differences between the groups ( P < .05). However, the OCTA features indicated early retinal changes in DWR eyes better than OCT ( P < .05). In the AI model using both OCT and OCTA features simultaneously, the best area under the curve of 0.91 ± 0.02 was obtained ( P < .05). Thus, the combined use of AI, OCT and OCTA significantly improved the early diagnosis of diabetic changes in the retina. Abstract : We used artificial intelligence (AI) to link OCT and OCTA features of diabetic changes in the human retina for early diagnosis of diabetic retinopathy (DR). We found that vascular changes preceded the onset of retinopathy and the inclusion of age match normal eyes was vital for the effective training of AI models. Further, imaging features for early diagnosis using combined OCT and OCTA imaging were identified for the first time.