A Semantic Query Approach for Diagnostic Image Database Management -Content-based Access and Knowledge Exchange Using XML

摘要

It is widely recognized that semantic query methods play an important role in image database retrieval. Prominent approaches using hierarchical semantic networks have been studied and applied to content-based image retrieval (CBIR) to narrow the gap between semantics and image features. Unfortunately, most of the studies lack the flexibility to adapt an individual's opinion to establish a general-purpose semantic network or to share the perceptual understanding with others. In this paper, we propose a semantic query system for diagnostic image database retrieval that uses physician-defined perceptual categories related to lung pathologies. Users are able to improve the quality of image retrieval by creating new semantic terms and adjusting search ranges derived from the predefined perceptual categories. The system brings an increased versatility for image retrieval, and a virtually unlimited number of possibilities for customizing the perceptual categories dictionary by using the flexibility and exchange capabilities of XML. Our unique approach provides various querying methods that use the perceptual categories within the domain of HRCT images of the lung and allows individual users to bring the contribution to the common knowledge in this domain.