ACM Computing Surveys (CSUR)
Fast Indexing and Visualization of Metric Data Sets using Slim-Trees
IEEE Transactions on Knowledge and Data Engineering
On Optimizing Nearest Neighbor Queries in High-Dimensional Data Spaces
ICDT '01 Proceedings of the 8th International Conference on Database Theory
How to Add Content-based Image Retrieval Capability in a PACS
CBMS '02 Proceedings of the 15th IEEE Symposium on Computer-Based Medical Systems (CBMS'02)
Foundations of Multidimensional and Metric Data Structures (The Morgan Kaufmann Series in Computer Graphics and Geometric Modeling)
SIREN: a similarity retrieval engine for complex data
VLDB '06 Proceedings of the 32nd international conference on Very large data bases
Efficient processing of complex similarity queries in RDBMS through query rewriting
CIKM '06 Proceedings of the 15th ACM international conference on Information and knowledge management
HEAD: The Human Encephalon Automatic Delimiter
CBMS '07 Proceedings of the Twentieth IEEE International Symposium on Computer-Based Medical Systems
Image retrieval: Ideas, influences, and trends of the new age
ACM Computing Surveys (CSUR)
Features for image retrieval: an experimental comparison
Information Retrieval
Overview of the ImageCLEFmed 2007 Medical Retrieval and Medical Annotation Tasks
Advances in Multilingual and Multimodal Information Retrieval
Natural language processing versus content-based image analysis for medical document retrieval
Journal of the American Society for Information Science and Technology
A classification-driven similarity matching framework for retrieval of biomedical images
Proceedings of the international conference on Multimedia information retrieval
Multimodal medical image retrieval: image categorization to improve search precision
Proceedings of the international conference on Multimedia information retrieval
Medical Image Categorization and Retrieval for PACS Using the GMM-KL Framework
IEEE Transactions on Information Technology in Biomedicine
Hi-index | 0.00 |
Medical systems increasingly demand methods to deal with the large amount of images that are daily generated. Therefore, the development of fast and scalable applications to store and retrieve images in large repositories becomes an important concern. Moreover, it is necessary to handle textual and content-based queries over such data coupled with DICOM image metadata and their visual patterns. While DBMSs have been extensively used to manage applications' textual information, content-based processing tasks usually rely on specific solutions. Most of these solutions are targeted to relatively small and controlled datasets, being unfeasible to be employed in real medical environments that deal with voluminous databases. Moreover, since in existing systems the content-based retrieval is detached from the DBMS, queries integrating content- and metadata-based predicates are executed isolated, having their results joined in additional steps. It is easy to realize that this approach prevent from many optimizations that would be employed in an integrated retrieval engine. In this paper we describe the MedFMI-SiR system, which handles medical data joining textual information, such as DICOM tags, and intrinsic image features integrated in the retrieval process. The goal of our approach is to provide a subsystem that can be shared by many complex data applications, such as data analysis and mining tools, providing fast and reliable content-based access over large sets of images. We present experiments that show that MedFMI-SiR is a fast and scalable solution, being able to quickly answer integrated content- and metadata-based queries over a terabyte-sized database with more than 10 million medical images from a large clinical hospital.