Guo Yukun, Camino Acner, Wang Jie, Huang David, Hwang Thomas S, Jia Yali
Casey Eye Institute, Oregon Health & Science University, Portland, OR 97239, USA.
Department of Biomedical Engineering, Oregon Health & Science University, Portland, OR 97239, USA.
Biomed Opt Express. 2018 Oct 2;9(11):5147-5158. doi: 10.1364/BOE.9.005147. eCollection 2018 Nov 1.
Screening and assessing diabetic retinopathy (DR) are essential for reducing morbidity associated with diabetes. Macular ischemia is known to correlate with the severity of retinopathy. Recent studies have shown that optical coherence tomography angiography (OCTA), with intrinsic contrast from blood flow motion, is well suited for quantified analysis of the avascular area, which is potentially a useful biomarker in DR. In this study, we propose the first deep learning solution to segment the avascular area in OCTA of DR. The network design consists of a multi-scaled encoder-decoder neural network (MEDnet) to detect the non-perfusion area in 6 × 6 mm and in ultra-wide field retinal angiograms. Avascular areas were effectively detected in DR subjects of various disease stages as well as in the foveal avascular zone of healthy subjects.
筛查和评估糖尿病视网膜病变（DR）对于降低糖尿病相关的发病率至关重要。已知黄斑缺血与视网膜病变的严重程度相关。最近的研究表明，光学相干断层扫描血管造影（OCTA）具有来自血流运动的固有对比度，非常适合对无血管区进行定量分析，而无血管区可能是DR中一种有用的生物标志物。在本研究中，我们提出了首个用于分割DR的OCTA中无血管区的深度学习解决方案。网络设计包括一个多尺度编码器-解码器神经网络（MEDnet），用于检测6×6毫米和超广角视网膜血管造影中的无灌注区。在不同疾病阶段的DR受试者以及健康受试者的黄斑无血管区中均能有效检测到无血管区。
