Automated Screening for Diabetic Retinopathy by Content

按内容自动筛查糖尿病视网膜病变

• 批准号: 7280326
• 负责人: EDWARD CHAUM
• 金额: $ 45.44万
• 依托单位: UNIVERSITY OF TENNESSEE HEALTH SCI CTR
• 依托单位国家: 美国
• 财政年份: 2005
• 资助国家: 美国
• 起止时间: 2005-09-30 至 2009-06-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/7280326
• 关键词: Agreement; Algorithms; Anatomy; Area; Blinded; Clinical; Clinical Research; Clinical Trials; Comparative Study; Computer Assisted; Computer-Assisted Image Analysis; Computers; Data; Data Analyses; Databases; Descriptor; Detection; Development; Diabetic Retinopathy; Diagnosis; Diagnostic; Diagnostic Imaging; Diagnostic Procedure; Discriminant Analysis; Disease; Early Diagnosis; Enrollment; Environment; Examinations and Diagnoses; Eye; Facility Construction Funding Category; Fundus; Goals; Human; Image; Image Analysis; Imagery; Investigation; Lesion; Libraries; Methodology; Methods; Mydriatics; Noise; Optic Nerve; Pathology; Patients; Procedures; Process; Protocols documentation; Research; Research Ethics Committees; Research Personnel; Retina; Retinal; Retinal Diseases; Retrieval; Screening procedure; Sensitivity and Specificity; Specialist; Statistical Methods; Statistically Significant; Structure; System; Technology; Testing; Visual; analytical tool; base; case-based; clinical Diagnosis; cohort; comparative; concept; cost; design; diabetic; digital; digital imaging; image processing; improved; indexing; macula; novel; prospective

DESCRIPTION (provided by applicant): The application of computer-based imaging to the diagnosis of retinal disease is rapidly becoming a reality. Advances in the imaging of ocular anatomy and pathology can now provide data to diagnose and quantify specific diseases including diabetic retinopathy. The potential for these digital technologies is clear, new computer based systems, and diagnostic algorithms hold the promise of producing low-cost, potentially automated, diagnostic imaging systems. The goal of this project is to investigate the feasibility of a content-based image retrieval (CBIR) method to accurately describe and index human retinal images of diabetic retinopathy collected from low-cost, nondilated retinal photographic examinations. Our goal is to demonstrate the feature-based indexing and retrieval process of CBIR and verify our hypothesis, and novel concept, that retinal pathology can be identified and quantified from visually similar retinal images assembled from a large database comprising images of diabetic retinopathy. The proposed research extends this fundamental investigation by incorporating intrinsic and extrinsic patient data to provide a diagnostic method. We have brought together a unique team that is currently designing the algorithms, developing the analytical tools, and performing the required clinical trials to reach the stated goals of this RFA.

描述（由申请人提供）：计算机成像在视网膜疾病诊断中的应用正迅速成为现实。眼部解剖和病理成像的进步现在可以为诊断和量化特定疾病提供数据，包括糖尿病视网膜病变。这些数字技术的潜力是显而易见的，新的基于计算机的系统和诊断算法有望产生低成本、潜在自动化的诊断成像系统。该项目的目的是研究一种基于内容的图像检索（CBIR）方法的可行性，以准确描述和索引从低成本，非扩张视网膜摄影检查中收集的糖尿病视网膜病变的人类视网膜图像。我们的目标是展示基于特征的CBIR索引和检索过程，并验证我们的假设和新概念，即视网膜病理可以从视觉上相似的视网膜图像中识别和量化，这些图像来自一个由糖尿病视网膜病变图像组成的大型数据库。拟议的研究扩展了这一基础调查，结合内在和外在的病人数据，以提供一种诊断方法。我们汇集了一个独特的团队，目前正在设计算法，开发分析工具，并执行所需的临床试验，以达到该RFA的既定目标。