Title: KMed: A Knowledge-Based Approach for Retrieving Medical Images by Features and Content

A knowledge-based approach is introduced for retrieving images by features content. It supports the answering of conceptual image queries involving similar-to, spatial and temporal operators, as well as conceptual terms. Interested objects in the images are represented by contours segmented from images. Image content such as shapes and spatial relationships are derived from object contours according to domain-specific image knowledge. The image features are classified by an automatic clustering algorithm and represented by Type Abstraction Hierarchies (TAHs) for knowledge-based query processing. Since features selected for TAH generation are based on context and user profile, and the TAHs can be generated automatically by a clustering algorithm from the feature database, our image retrieval approach is scalable and context-sensitive. Further, since TAHs are generated based on user classes and applications, they are context- and user-sensitive. A knowledge-based semantic image model is used that consists of four layers (raw data layer, feature and content layer, schema layer, and knowledge layer) to represent the various aspects of an image object's characteristics. The model proves a mechanism for accessing and processing spatial, evolutionary, and temporal queries. A knowledge-based spatial temporal query language (KSTL) has been developed that supports approximate matching of feature and content, conceptual terms, and temporal logic predicates. Further, a visual query language has been developed that accepts point-click-and-drag visual iconic input on the screen that is then translated into KSTL. User models are introduced to provide default parameter values for specifying query conditions. We have implemented a Knowledge-Base Medical Database System (KMeD) at UCLA, and it is currently under evaluation by the medical staff for clinical applications.
Bio-sketch:
Dr. Wesley W. Chu is a professor of Computer Science and was the past chairman (1988-1991) of the Computer Science Department at the University of California, Los Angles. He received his B.S.E. (EE) and M.S.E. (EE) from the University of Michigan and his Ph.D. (EE) from Stanford University..
From 1964 to 1966, he worked on the design of large-scale computers at IBM, Menlo Park and San Jose, California. From 1966 to 1969, he researched computer communications and distributed databases at Bell Laboratories, Holmdel, New Jersey. He joined the University of California, Los Angeles in 1969. He directs a research group at UCLA in the areas of knowledge-based multimedia information systems, intelligent web-based databases, and data mining of large information projects. He has authored or co-authored more than 100 articles on information processing systems and has edited three textbooks: in Computer Communications, Distributed Processing and Distributed Data Bases He is currently a PI on an interdisciplinary project for mining the temporal and spatial of input/output relationships of dynamic systems. He is also a co-PI and the project leader of the NIH PPG grant for developing a medical digital library.
Dr. Chu is a Fellow of IEEE. He was an associate editor for the IEEE Transactions on Computers for the field of computer networking and distributed processing systems (1978-1982) and received a meritorious award for his service to the IEEE (1983). He was the workshop co-chair of the IEEE First International Workshop on Systems Management, April 1993, and received a Certificate of Appreciation award for his significant service. He was the conference chair of the 16th International Conference on Conceptual Modeling (ER'97) and a member of the Editorial Board of the Journal on Very Large Data Bases. He is currently an Associate Editor for the Journal of Data and Knowledge Engineering, and the International Journal of Applied Intelligence.