Advanced Image Analysis Tools for Diabetic Retinopathy Telemedicine Applications

用于糖尿病视网膜病变远程医疗应用的高级图像分析工具

基本信息

批准号：
8266132
负责人：
Kaushal Solanki
金额：
$ 19.99万
依托单位：
EYENUK, INC.
依托单位国家：
美国
项目类别：
财政年份：
2012
资助国家：
美国
起止时间：
2012-05-08 至 2014-04-30
项目状态：
已结题

来源：
https://reporter.nih.gov/project-details/8266132
关键词：
Address Agreement Algorithms Appointment Architecture Area Arts Awareness Blindness California Car Phone Clinic Clinical Code Complications of Diabetes Mellitus Computer Vision Systems Computer software Consult County Detection Diabetes Mellitus Diabetic Retinopathy Dictionary Disadvantaged Economic Factors Ensure Exudate Eye Faculty Feedback Goals Gold Health Healthcare Hemorrhage Hispanics Human Image Image Analysis Incidence Institutes Insurance Coverage Internet Joints Latino Lesion Localized Lesion Location Los Angeles Machine Learning Measures Medical center Microaneurysm Online Systems Ophthalmologist Optometry Patient Education Patients Phase Plug-in Population Populations at Risk Primary Health Care Principal Investigator Process ROC Curve Reading Reproducibility Research Research Infrastructure Research Project Grants Retinal Diseases Risk Rural Rural Health Screening procedure Sensitivity and Specificity Severities Side Small Business Innovation Research Grant Software Design Software Engineering Software Tools Statistical Computing System Telemedicine Testing Time Universities Work abstracting base bioimaging computerized data processing cost cotton wool spots diabetes risk experience image processing neovascularization prevent prototype socioeconomics success tool tv watching user-friendly web interface

项目摘要

DESCRIPTION (provided by applicant): Abstract In this small business innovations research (SBIR) project, we present aiArt: Advanced Image Analysis Tools for Diabetic Retinopathy Telemedicine applications. aiArt (pronounced eye-art), with its automated image analysis tools and user-friendly telemedicine web-interface, will enable exponential expansion of diabetic retinopathy screenings, thus fulfilling a significant health need as the number of people with diabetes climbs over the years. Latino population is genetically more prone to diabetes. Factors such as lack of awareness, lack of insurance coverage, and lack of access to expert clinicians greatly increase this disparity population's vulnerability to blindness due to DR. The situation is particularly grim in Los Angeles County, where there is a backlog of several thousand patients waiting to see an ophthalmologist, causing very long appointment wait times (often over six months). To help reduce risk of vision loss in this population, we propose to use advanced image analysis algorithms in conjunction with existing telemedicine initiatives to enable faster screening, allow reprioritization of ophthalmologist appointments, and to provide patient education tools. Our automated image analysis algorithms represent cutting-edge of research in image processing, computer vision, and machine learning. The analysis engine will be closely integrated with simple, easy-to-use web-based telemedicine infrastructure provided by an existing, popular, telemedicine initiative, EyePACS. PUBLIC HEALTH RELEVANCE: Narrative The proposed image analysis tools will greatly reduce the cost of diabetic retinopathy screening, and with its web and mobile phone accessible interface will drive an expansion of diabetic retinopathy screening, making it accessible to disparity populations (such as Latinos) which are not currently being screened due to socio-economic factors. The proposed tools will also enable quick turnaround time for screening, thus further helping prevent blindness due to diabetes complications.

描述（由申请人提供）：在这个小型企业创新研究（SBIR）项目中摘要，我们介绍了AIART：用于糖尿病性视网膜病变远程医疗应用的高级图像分析工具。 AIART（发音为眼睛），其自动图像分析工具和用户友好的远程医疗网络接口将实现糖尿病性视网膜病变筛查的指数扩展，从而满足了多年来糖尿病的人数，因此满足了巨大的健康需求。拉丁裔人口在遗传上更容易容易患糖尿病。诸如缺乏认识，缺乏保险范围以及缺乏专业临床医生的访问权的因素会大大增加了由于DR引起的差异人群易受盲人的脆弱性。情况是在洛杉矶县特别严峻，那里有数千名患者的积压，等待着眼科医生，这导致了很长的约会等待时间（通常超过六个月）。为了减少该人群中视力丧失的风险，我们建议将高级图像分析算法与现有的远程医疗计划结合使用，以更快地进行筛查，允许眼科医生的任命重新定位并提供患者教育工具。我们的自动图像分析算法代表了图像处理，计算机视觉和机器学习中研究的尖端。分析引擎将与简单，易于使用的基于Web的远程医疗基础架构紧密整合，由现有的，受欢迎的，远程医疗的倡议（Eyepacs）提供。公共卫生相关性：叙述所提出的图像分析工具将大大降低糖尿病性视网膜病变筛查的成本，并且其网络和手机无障碍界面将推动糖尿病性视网膜病变筛查的扩展，从而使差异群体（例如Latinos）易于筛查，而这些视差群体目前由于社会经济因素而被筛查。所提出的工具还将为筛查的快速周转时间提供，从而进一步帮助预防糖尿病并发症引起的失明。