This paper describes an interactive system for the semantic annotation of brain magnetic resonance images. The system uses both a numerical atlas and symbolic knowledge of brain anatomical structures depicted using the Semantic Web standards. This knowledge is combined with graphical data, automatically extracted from the images by imaging tools. The annotations of parts of gyri and sulci, in a region of interest, rely on constraint satisfaction problem solving and description logics inferences. The system is run on a client-server architecture, using Web services and including a sophisticated visualization tool. An evaluation of the system was done using normal (healthy) and pathological cases. The results obtained so far demonstrate that the system produces annotations with high precision and quality.

The work concerns a framework for the formal specification and verification of the dynamic knowledge of knowledge-based systems. At a conceptual level, a system is specified in terms of problems, problem-solving processes, knowledge. An important question is to determine if a process is applicable to solve a problem. In this paper we present how problems and problem-solving processes are specified by abstract data types and we introduce a formalization of the relationships between them. We show how it can be formally proved that a process is correct with respect to a given problem.

The paper presents the TASK framework which is intended to cover the life cycle of a knowledge based system. TASK provides: (i) a conceptual language which enables an informal specification at the knowledge level; (ii) a formal language TFL which permits an unambiguous specification; and (iii) an operational shell TASK/sup +/ which allows an efficient execution even for badly structured problems. The paper presents the different languages, the links between them and emphasizes the implementation stage. We show how TASK proposes a nice compromise solution between efficiency and expressivity.