Diagnostic Aid Software for Visual Field Test

视野测试诊断辅助软件

• 批准号: 6582662
• 负责人: Dariusz Wroblewski
• 金额: $ 9.97万
• 依托单位: INTELLIGENT AUTOMATION CORPORATION
• 依托单位国家: 美国
• 财政年份: 2003
• 资助国家: 美国
• 起止时间: 2003-01-01 至 2003-06-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/6582662
• 关键词: artificial intelligence; computer assisted diagnosis; computer program /software; computer system design /evaluation; diagnosis design /evaluation; early diagnosis; glaucoma; glaucoma test; human data; noninvasive diagnosis; vision tests; visual fields

DESCRIPTION (provided by applicant): Visual Field (VF) test is a widely used, noninvasive technique for evaluating pathology or dysfunction in the visual pathways. The VF test, in conjunction with other diagnostics, is used for detection of early stages of glaucoma and for following its progression. Early detection is critical as blindness from glaucoma is preventable in nearly all cases, provided treatment is administered early in the progression. However, the inherent subjectivity of the VF test makes it often difficult to interpret even for a skilled practitioner. There is a need for automated decision aid tool that will facilitate and standardize the interpretation task. In Phase 1 of this project, IAC will design and implement novel software algorithms to automate the interpretation of VF test data for detection of glaucoma. The software will classify VF test data into normal, borderline glaucomatous, glaucomatous and unknown (not normal or glaucomatous). The aim is to provide classification performance close to that of a highly skilled human expert. The emphasis will be on the detection of early stages of glaucoma. In addition to the classification output, the software will produce a set of comprehensive rules that will explain the decision path leading to the suggested diagnosis.

描述（由申请人提供）：视野（VF）测试是一种广泛使用的非侵入性技术，用于评价视觉通路中的病理或功能障碍。VF测试，结合其他诊断，用于检测青光眼的早期阶段，并跟踪其进展。早期发现是至关重要的，因为青光眼致盲在几乎所有情况下都是可以预防的，只要在进展的早期给予治疗。然而，VF测试固有的主观性使得即使对于熟练的从业者也常常难以解释。需要有一种自动化的辅助决策工具，以便利口译工作并使之标准化。 在该项目的第一阶段，IAC将设计和实施新的软件算法，以自动解释VF测试数据，用于检测青光眼。软件将VF测试数据分类为正常、临界昏迷、昏迷和未知（不正常或昏迷）。其目的是提供接近于高度熟练的人类专家的分类性能。重点将放在早期青光眼的检测上。除了分类输出外，软件还将产生一组综合规则，解释导致建议诊断的决策路径。