From generic knowledge to specific reasoning for medical image interpretation using graph based representations

In several domains of spatial reasoning, such as medical image interpretation, spatial relations between structures play a crucial role since they are less prone to variability than intrinsic properties of structures. Moreover, they constitute an important part of available knowledge. We show in this paper how this knowledge can be appropriately represented by graphs and fuzzy models of spatial relations, which are integrated in a reasoning process to guide the recognition of individual structures in images. However pathological cases may deviate substantially from generic knowledge. We propose a method to adapt the knowledge representation to take into account the influence of the pathologies on the spatial organization of a set of structures, based on learning procedures. We also propose to adapt the reasoning process, using graph based propagation and updating.