This poster is published under an
open license. Please read the
disclaimer for further details.
Type:
Educational Exhibit
Keywords:
Computer applications, Image manipulation / Reconstruction, CAD, Computer Applications-Detection, diagnosis, Statistics, Education and training, Epidemiology
Authors:
H. Müller1, E. Kotter2; 1Sierre/CH, 2Freiburg/DE
DOI:
10.1594/ecr2015/C-1335
Findings and procedure details
In radiology,
RadLex [2] has been created to standardize annotation of images and thus reuse.
One example of RadLex use is structured reporting where templates for many domains and types of observations exist and reusing the templates can significantly increase efficiency.
Another area of RadLex use is information retrieval,
where semantic knowledge of cases can make it much easier to find a specific case with a particular visual observation or a specific disease,
again taking into account synonyms and also sub categories of a disease or a specific imaging modality.
The Render Project [3] the RadMining Project [4] and the Medico Project [5] have shown the feasibility of semantic image search in medicine.
Also the Radiology search engine Goldminer [6] is able to map images onto RadLex terms for better search.
Imaging modality can be determined also in the biomedical scientific literature using semantic terms and this allows to link the literature for example with specific cases of clinical routine as is one of the goals of the Khresmoi project [7].