Automated Screening for Diabetic Retinopathy by Content*

描述(申请人提供)：计算机成像在视网膜疾病诊断中的应用正在迅速成为现实。眼部解剖和病理学成像的进展现在可以为诊断和量化包括糖尿病视网膜病变在内的特定疾病提供数据。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，而诊断算法拥有生产低成本、潜在自动化的诊断成像系统的前景。本项目的目标是研究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、非扩张性视网膜照相检查中收集的糖尿病视网膜病变的人类视网膜图像。我们的目标是演示CBIR的基于特征的索引和检索过程，并验证我们的假设和新概念，即可以从包含糖尿病视网膜病变图像的大型数据库中收集视觉相似的视网膜图像来识别和量化视网膜病变。拟议的研究通过结合内在和外在的患者数据来扩展这一基础调查，以提供一种诊断方法。我们汇集了一个独特的团队，该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，以达到本RFA规定的目标。

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.