Content based image retrieval in medical applications: an improvement of the two-level architecture

Medical imaging is specific part of medicine according to the medical images features. This is the reason for growing up requirements for improvement of Content Based Image Retrieval (CBIR) systems applied on medical images. Improving these systems is one of the biggest challenges for scientists in this domain. In this paper we propose an extension and improvement of the existing two-level CBIR architecture proposed. The proposed improvement of the two-level architecture is expected to increase the accuracy of the retrieval results.