A Cooperative, Spatial, and Evolutionary Medical Database System

协作、空间和进化的医学数据库系统

• 批准号: 9224559
• 负责人: Wesley Chu
• 金额: $ 40.5万
• 依托单位: University of California-Los Angeles
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 1993
• 资助国家: 美国
• 起止时间: 1993-08-01 至 1997-07-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=9224559&HistoricalAwards=false
• 关键词: Cooperative; Spatial; Evolutionary; Medical; Database

9224559 Chu SDB: A Cooperative, Spatial, and Evolutionary Biomedical Database System This is the first year funding of a three-year continuing award. The objective of this research is to develop a distributed knowledge-based multimedia database system for biomedical applications with cooperative query answering capabilities. The system will be able to access data in image databases by content (features, objects, etc.). In particular, the proposed data model captures spatial and evolutionary semantics and thus greatly enhances high-level query capabilities. The image objects and their features are obtained from segmentation software and are stored in the database. Using rules derived from domain knowledge, approximate and conceptual queries may be answered. Additional information relevant to a query cay be provided by associating different hierarchies of subjects. Type abstraction hierarchies (TAHs) generalize a query's scope while the relaxation control, based on user profiles and query context, trims the TAHs and keeps the generalizations manageable and appropriate. An explanation system tracks the relaxation path and provides a measure of the nearness of the approximate answer to the exact one. These concepts are validated in a testbed linked with radiology image databases. The joint research between the UCLA Computer Science Department and the School of Medicine assures that the prototype systems are of direct interest to radiology research and practice. The results of this research are extensible to other multimedia database applications. ***

9224559 Chu SDB：合作、空间和进化的生物医学数据库系统这是一个为期三年的持续资助项目的第一年。本研究的目标是开发一个具有协同查询应答功能的分布式生物医学多媒体数据库系统。系统将能够根据内容（特征、对象等）访问图像数据库中的数据。特别地，所提出的数据模型捕获了空间和进化语义，从而大大增强了高级查询功能。图像对象及其特征由分割软件获取并存储在数据库中。使用从领域知识派生的规则，可以回答近似和概念查询。可以通过关联主题的不同层次结构来提供与查询相关的其他信息。类型抽象层次结构（TAHs）泛化查询的范围，而基于用户配置文件和查询上下文的放松控制则对TAHs进行修整，并使泛化保持可管理和适当。解释系统跟踪松弛路径，并提供近似答案与精确答案的接近程度的度量。这些概念在与放射学图像数据库连接的试验台中得到验证。加州大学洛杉矶分校计算机科学系和医学院的联合研究确保了原型系统对放射学研究和实践的直接兴趣。本文的研究结果可推广到其他多媒体数据库的应用中。＊＊＊