Automated Retinal Analysis for Detection of Age Related Macular Degeneration

用于检测年龄相关性黄斑变性的自动视网膜分析

基本信息

批准号：
8998947
负责人：
Neil Michael Bressler
金额：
$ 18.01万
依托单位：
JOHNS HOPKINS UNIVERSITY
依托单位国家：
美国
项目类别：
财政年份：
2015
资助国家：
美国
起止时间：
2015-02-01 至 2017-12-31
项目状态：
已结题

来源：
https://reporter.nih.gov/project-details/8998947
关键词：
Adult Age related macular degeneration Algorithms Artificial Intelligence Biotechnology Blindness Caring Cataract Classification Clinical Clinical Research Clinical Treatment Computer software Computers Data Data Set Detection Development Diabetic Retinopathy Discipline Drusen Evaluation Evolution Eye Eye diseases Funding Fundus Generations Goals Grant Health Image Image Analysis Individual Institutes Laboratories Lead Left Life Lighting Machine Learning Medical Methods Monitor Morphologic artifacts Myopia National Eye Institute Ophthalmologist Participant Pathology Patients Performance Physicians Physics Pigmentation physiologic function Population Principal Investigator Procedures Provider Public Health Research Personnel Retina Retinal Risk Scientist Severities Site Software Tools Staging Structure of retinal pigment epithelium Testing Universities Validation Vision Work age related bioimaging computer program database of Genotypes and Phenotypes design dietary supplements experience follow-up geographic atrophy improved improved outcome neovascular novel programs response screening tool

项目摘要

DESCRIPTION (provided by applicant): This study focuses on age-related macular degeneration (AMD) because, left untreated, it is the leading cause of blindness in the adult US population over 50. The goals of this program are twofold. First, the focus is to develop new screening tools to detect individuals with the intermediate stage of AMD, that are otherwise asymptomatic for vision loss, at a stage where they can be referred to a clinician for treatment and follow up, and when vision more likely can be preserved. The second goal is to develop Automated Retinal Image Analysis (ARIA) tools that help characterize Geographic Atrophy (GA), for which novel treatments are being investigated. We are developing data-driven algorithms for AMD screening which leverage recent advances in machine learning and machine intelligence and do not rely on detecting and counting or sizing drusen (a procedure which can be error prone). Instead, our method analyzes a fundus image as a whole using an image classification paradigm, and may also exploit ancillary patient information. Our goal is to use the AREDS dbGaP that includes thousands of images from hundreds of patients and offers a unique opportunity to develop and test these algorithms on a scale that has not previously been possible. Our team consists of the Johns Hopkins Wilmer Eye Institute, which will serve as the clinical analysis test site, and the Johns Hopkins University Applied Physics Laboratory, which will conduct the automated screening software tool analysis, development and testing.

描述（由适用提供）：本研究的重点是与年龄相关的黄斑变性（AMD），因为未经治疗，这是美国成年美国人口50岁以上失明的主要原因。该计划的目标是双重的。首先，重点是开发新的筛选工具来检测具有AMD中间阶段的个体，这些筛选工具是视力丧失的不对称性，在可以转介给临床治疗和随访的阶段，并且更有可能保留视力时。第二个目标是开发自动化的视网膜图像分析（ARIA）工具，以帮助表征地理萎缩（GA），为此研究了新的治疗方法。我们正在开发用于AMD筛选的数据驱动算法，该算法利用机器学习和机器智能的最新进展，并且不依赖于检测和计数或计数或尺寸drusen（可能是错误的过程）。取而代之的是，我们的方法使用图像分类范式分析了整个底面图像，并且也可能利用辅助患者信息。我们的目标是使用包括数百名患者的数千张图像的AREDS DBGAP，并提供了一个独特的机会来开发和测试这些算法的规模，以前尚未实现。我们的团队由约翰·霍普金斯·威尔默眼科研究所（John Hopkins Wilmer Eye Institute）组成，该研究所将用作临床分析测试站点，约翰·霍普金斯大学应用物理实验室将进行自动筛选软件工具分析，开发和测试。