Automated Image-based Biomarker Computation Tools for Diabetic Retinopathy

用于糖尿病视网膜病变的基于图像的自动化生物标志物计算工具

• 批准号: 9104250
• 负责人: Kaushal Solanki
• 金额: $ 48.34万
• 依托单位: EYENUK, INC.
• 依托单位国家: 美国
• 财政年份: 2012
• 资助国家: 美国
• 起止时间: 2012-09-01 至 2017-06-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/9104250
• 关键词: Address; Adult; Age; Agreement; Appearance; Area; Biological; Biological Markers; Blindness; California; Caring; Classification; Clinical; Clinical Research; Cloud Computing; Computer software; Consult; Consultations; County; Data Set; Detection; Diabetic Retinopathy; Early Diagnosis; Early identification; Effectiveness; Eye; Face; Faculty; Fundus; Goals; Health; Health Services; Human; Image; Image Analysis; Imagery; Individual; Institutes; Intervention; Joints; Lesion; Life; Los Angeles; Manuals; Marketing; Measurement; Measures; Microaneurysm; Monitor; Ophthalmic examination and evaluation; Ophthalmology; Optometry; Patients; Performance; Phase; Population; Process; Recruitment Activity; Reporting; Research; Retinal; Retinal Diseases; Risk; Small Business Innovation Research Grant; Small Business Technology Transfer Research; Software Engineering; Staging; Surveys; Tablets; Testing; Time; Universities; Work; base; bioimaging; clinical care; commercialization; design; diabetic; diabetic patient; drug discovery; experience; follow-up; high risk; image processing; image registration; improved; industry partner; non-invasive imaging; novel; novel therapeutics; prevent; programs; prototype; screening; secondary outcome; statistics; success; tool; usability; validation studies

DESCRIPTION (provided by applicant): In this STTR project, we present EyeMark, a set of advanced image analysis tools for automated computation of biomarkers for diabetic retinopathy (DR) using retinal fundus images. Specifically, we will develop tools for computation of microaneurysm (MA) appearance and disappearance rates (jointly known as turnover rates) for use as a biomarker in quantifying DR progression risk. The availability of a reliable image-based biomarker will have high positive influence on various aspects of DR care, including screening, monitoring progression, drug discovery and clinical research. Measuring MA turnover involves two labor intensive steps: careful alignment of current and baseline images, and marking of individual MAs. This process is very time consuming and prone to error, if done entirely by human graders. The primary goal of this project is to overcome these limitations by automating both the steps involved in MA turnover measurement: accurate image registration, and MA detection. In Phase I we have designed and developed a MA turnover computation prototype tool that robustly registers longitudinal images (even with multiple lesion changes) and effectively detects MAs (lesion level AUROC=0.92). The tool provides graceful degradation to confounding image factors by reporting MA turnover as a range, thereby capturing the inherent confidence in MA detection. By the end of Phase II we will develop a clinically validated end-to-end desktop software for robust, automated computation of MA turnover biomarker, that can work on the cloud to produces results in near constant time (for large datasets), and also provide intuitive visualization tools for clinicians to more effectively monitor DR progression.

描述（由申请人提供）：在这个 STTR 项目中，我们展示了 EyeMark，这是一套先进的图像分析工具，用于使用视网膜眼底图像自动计算糖尿病视网膜病变 (DR) 的生物标志物。具体来说，我们将开发用于计算微动脉瘤 (MA) 出现率和消失率（统称为周转率）的工具，以用作量化 DR 进展风险的生物标志物。可靠的基于图像的生物标志物的可用性将对 DR 护理的各个方面产生高度积极的影响，包括筛查、监测进展、药物发现和临床研究。 测量 MA 周转率涉及两个劳动密集型步骤：仔细对齐当前图像和基线图像，以及标记各个 MA。如果完全由人工评分者完成，这个过程非常耗时并且容易出错。该项目的主要目标是通过自动化 MA 周转测量中涉及的两个步骤来克服这些限制：准确的图像配准和 MA 检测。 在第一阶段，我们设计并开发了一种 MA 周转计算原型工具，该工具可以稳健地记录纵向图像（即使有多个病变变化）并有效检测 MA（病变级别 AUROC=0.92）。该工具通过将 MA 周转率报告为范围来提供对混杂图像因素的优雅降级，从而捕获 MA 检测的固有置信度。到第二阶段结束时，我们将开发一款经过临床验证的端到端桌面软件，用于稳健、自动计算 MA 周转生物标志物，该软件可以在云上工作，在接近恒定的时间内（针对大型数据集）产生结果，并为临床医生提供直观的可视化工具，以更有效地监测 DR 进展。