Imaging, Biomechanics and Mathematical Modeling solutions Lab, Narayana Nethralaya Foundation, Bangalore, India.
Department of Vitreoretinal Diseases, Sankara Nethralaya, Chennai, India.
J Biophotonics. 2020 Sep;13(9):e202000107. doi: 10.1002/jbio.202000107. Epub 2020 Jun 18.
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.
本研究旨在利用人工智能（AI）评估糖尿病患者的早期血管和断层变化。研究纳入了 74 例年龄匹配的正常眼、171 例无糖尿病视网膜病变（DR）的糖尿病眼和 69 例轻度非增生性糖尿病视网膜病变（NPDR）。所有患者均接受了光学相干断层扫描血管造影（OCTA）成像。断层特征（厚度和体积）来自 OCTA B 扫描。这些特征被用于 AI 模型中。OCT 和 OCTA 特征在各组之间均显示出显著差异（P<0.05）。然而，OCTA 特征比 OCT 更能早期提示 DWR 眼中的视网膜变化（P<0.05）。在同时使用 OCT 和 OCTA 特征的 AI 模型中，获得了最佳的曲线下面积 0.91±0.02（P<0.05）。因此，AI、OCT 和 OCTA 的联合使用显著提高了糖尿病视网膜早期病变的诊断能力。
