Differential artery-vein analysis in OCT angiography for objective classification of diabetic retinopathy

OCT 血管造影中的动静脉差异分析用于糖尿病视网膜病变的客观分类

基本信息

批准号：
10080731
负责人：
Jennifer Irene Lim
金额：
$ 35.17万
依托单位：
UNIVERSITY OF ILLINOIS AT CHICAGO
依托单位国家：
美国
项目类别：
财政年份：
2020
资助国家：
美国
起止时间：
2020-02-01 至 2024-01-31
项目状态：
已结题

来源：
https://reporter.nih.gov/project-details/10080731
关键词：
Adult Affect Angiography Area Arteries Biological Markers Blindness Blood Vessels Blood capillaries Caliber Classification Clinical Color Complex Derivation procedure Detection Diabetes Mellitus Diabetic Retinopathy Disease Early Diagnosis Evaluation Exudate Eye diseases Fostering Fundus photography Geometry Health Expenditures Individual Intervention Investigation Machine Learning Maps Methods Microaneurysm Modernization Ophthalmologist Optical Coherence Tomography Optics Performance Process Reflex action Retina Retinal Edemas Retinal Hemorrhage Sensitivity and Specificity Source Staging Standardization Symptoms Techniques Telemedicine Testing Thinness Translating Treatment outcome Vascular Endothelial Growth Factors Veins Venous Visual Width base bevacizumab clinical biomarkers convolutional neural network deep neural network density design diabetic diabetic patient experience fovea centralis fundus imaging global health image registration imaging capabilities improved indexing instrument macular edema predictive marker prevent rural area success support vector machine underserved area vascular abnormality

项目摘要

Abstract: This project aims to establish differential artery-vein analysis in optical coherence tomography angiography (OCTA), and to validate comprehensive OCTA features for automated classification of diabetic retinopathy (DR). Early detection, prompt intervention, and reliable assessment of treatment outcomes are essential to prevent irreversible visual loss from DR. It is known that DR can target arteries and veins differently. Therefore, differential artery-vein analysis can provide better performance of DR detection and classification. However, clinical OCTA instruments lack the capability of artery-vein differentiation. During this project, we propose to use quantitative feature analysis of OCT, which is concurrently captured with OCTA, to guide artery- vein differentiation in OCTA. The first aim is to establish automated artery-vein differentiation in OCTA. In coordination with our recently demonstrated blood vessel tracking technique, OCT intensity/geometry features will be used to guide artery-vein differentiation in OCTA automatically. Differential artery-vein analysis of blood vessel tortuosity (BVT), blood vessel caliber (BVC), blood vessel density (BVD), vessel perimeter index (VPI), vessel branching coefficient (VBC), vessel branching angle (VBA), branching width ratio (BWR), fovea avascular zone area (FAZ-A) and FAZ contour irregularity (FAZ-CI) will be implemented. Key success criterion of the aim 1 study is to demonstrate robust artery-vein differentiation in OCTA, and to establish OCTA features for objective detection and classification of DR. The second aim is to validate automated OCTA classification of DR. We propose to employ ensemble machine learning to integrate multiple classifiers to achieve robust OCTA classification of DR. Key success criterion of the aim 2 study is to identify OCTA features and optimal-feature- combination to detect early DR, and to establish the correlations between the OCTA features and clinical biomarkers. The third aim is to verify OCTA prediction and evaluation of DR treatment. Our preliminary OCTA study of diabetic macular edema (DME) with anti-vascular endothelial growth factor (anti-VEGF) treatment has shown that BVD can serve as a biomarker predictive of visual improvement. During this project, we plan to test differential artery-vein analysis for DME treatment evaluation. Key success criterion of the aim 3 study is to identify artery-vein features to provide robust prediction and evaluation of DME treatment outcomes. As an alternative approach, we propose a fully convolutional neural network (FCNN) for deep machine leaning based artery-vein and DR classification. Early layers in the FCNN will produce simple features, which will be convolved and filtered into deeper layers to produce complex features for artery-vein and DR classification. Further investigation of the relationship between the new features learned through the machine learning process and clinical biomarkers will allow us to optimize the design for better DR classification. Success of this project will pave the way towards using quantitative OCTA features for early DR detection, objective prediction and assessment of treatment outcomes.

摘要：该项目旨在建立光学相干断层扫描中的差分动静脉分析血管造影 (OCTA)，并验证糖尿病自动分类的综合 OCTA 特征视网膜病变（DR）。早期发现、及时干预和对治疗结果的可靠评估是对于防止 DR 造成不可逆转的视力丧失至关重要。众所周知，DR 可以以不同的方式针对动脉和静脉。因此，差分动静脉分析可以提供更好的DR检测和分类性能。然而，临床OCTA仪器缺乏动静脉区分能力。在这个项目期间，我们建议使用与 OCTA 同时捕获的 OCT 定量特征分析来引导动脉 OCTA 中的静脉分化。第一个目标是在 OCTA 中建立自动动静脉区分。在与我们最近展示的血管跟踪技术、OCT 强度/几何特征相协调将用于自动引导 OCTA 中的动静脉分化。血液的动静脉差异分析血管迂曲度（BVT）、血管口径（BVC）、血管密度（BVD）、血管周长指数（VPI）、血管分支系数 (VBC)、血管分支角度 (VBA)、分支宽度比 (BWR)、中央凹无血管将实施区域区域（FAZ-A）和FAZ轮廓不规则（FAZ-CI）。目标的关键成功标准 1 项研究旨在证明 OCTA 中强大的动静脉分化，并建立客观的 OCTA 特征 DR 的检测和分类。第二个目标是验证 DR 的自动 OCTA 分类。我们建议采用集成机器学习来集成多个分类器以实现鲁棒的 OCTA DR的分类目标 2 研究的关键成功标准是识别 OCTA 特征和最佳特征联合检测早期 DR，并建立 OCTA 特征与临床之间的相关性生物标志物。第三个目标是验证 OCTA 对 DR 治疗的预测和评估。我们初步的 OCTA 使用抗血管内皮生长因子（抗 VEGF）治疗糖尿病性黄斑水肿（DME）的研究已表明 BVD 可以作为预测视力改善的生物标志物。在这个项目期间，我们计划测试用于 DME 治疗评估的差分动静脉分析。目标 3 研究的关键成功标准是识别动静脉特征，为 DME 治疗结果提供可靠的预测和评估。作为一个另一种方法是，我们提出了一种基于深度机器学习的全卷积神经网络（FCNN）动静脉和 DR 分类。 FCNN 中的早期层将产生简单的特征，这些特征将被卷积并过滤到更深的层以产生用于动静脉和 DR 分类的复杂特征。更远研究通过机器学习过程学到的新特征之间的关系临床生物标志物将使我们能够优化设计以实现更好的 DR 分类。该项目的成功将为使用定量 OCTA 特征进行早期 DR 检测、客观预测和评估治疗结果。