TY  - JOUR
ID  - MRG2005
T1  - Benefits from content-based visual data access in radiology
A1  - Müller, Henning
A1  - Rosset, Antoine
A1  - Garcia, Arnaud
A1  - Vallée, Jean-Paul
A1  - Geissbuhler, Antoine
JA  - radiographics
Y1  - 2005
VL  - 25
IS  - 3
SP  - 849
EP  - 858
SN  - 1527-1323
M2  - doi: 10.1148/rg.253045071
KW  - Medical image analysis and retrieval
KW  - Multimodal information retrieval and information fusion
N2  - The field of medicine is often cited as an area for which content-based visual retrieval holds considerable promise. To date, very few visual image retrieval systems have been used in clinical practice; the first applications of image retrieval systems in medicine are currently being developed to complement conventional text-based searches. An image retrieval system was developed and integrated into a radiology teaching file system, and the performance of the retrieval system was evaluated, with use of query topics that represent the teaching database well, against a standard of reference generated by a radiologist. The results of this evaluation indicate that content-based image retrieval has the potential to become an important technology for the field of radiology, not only in research, but in teaching and diagnostics as well. However, acceptance of this technology in the clinical domain will require identification and implementation of clinical applications that use content-based access mechanisms, necessitating close cooperation between medical practitioners and medical computer scientists. Nevertheless, content-based image retrieval has the potential to become an important technology for radiology practice.
ER  -