Title :
Automatic Image Annotation Combining the Content and the Context of Medical Images
Author :
Florea, Filip ; Buzuloiu, Vasile ; Rogozan, Alexandrina ; Bensrhair, Abdelaziz ; Darmoni, Stefan
Author_Institution :
Syst. Lab., Rouen
Abstract :
In this paper we evaluate the relevance of the information extracted from the visual content of medical images and from the image-related text-regions, as well as the performance gain obtained by combining the two approaches. First we annotate the images using a content-based annotation method that relies on the supervised classification of reduced visual representations derived from statistic and texture features. The context of medical images (i.e. image-related text regions) is extracted from the documents and analyzed using the MeSH medical ontology, which we improved and adapted to be able to extract specific category terms. Several ways of combining the two approaches are proposed and tested, showing significant overall annotation improvements.
Keywords :
content-based retrieval; feature extraction; image classification; image retrieval; image texture; learning (artificial intelligence); medical image processing; medical information systems; ontologies (artificial intelligence); statistical analysis; text analysis; content-based image annotation; image-related text region; information extraction; medical image processing; medical ontology; statistical analysis; supervised classification; texture feature; visual content; Biomedical imaging; Content based retrieval; Data mining; Hospitals; Image analysis; Image retrieval; Indexing; Information retrieval; Laboratories; Ontologies;
Conference_Titel :
Signals, Circuits and Systems, 2007. ISSCS 2007. International Symposium on
Conference_Location :
Iasi
Print_ISBN :
1-4244-0969-1
Electronic_ISBN :
1-4244-0969-1
DOI :
10.1109/ISSCS.2007.4292712