2004
@article{MRV2004,
vgclass = {refpap},
vgproject = {cbir},
author = {Henning M\"{u}ller and Antoine Rosset and Jean-Paul
Vall\'{e}e and Fran\c{c}ois Terrier and Antoine Geissbuhler},
title = {A reference data set for the evaluation of medical image
retrieval systems},
journal = {Computerized Medical Imaging and Graphics},
year = {2004},
note = {(in press)},
abstract = {Content-based image retrieval is starting to become an
increasingly important factor in medical imaging research and image
management systems. Several retrieval systems and methodologies exist
and are used in a large variety of applications from automatic
labelling of images to diagnostic aid and image classification. Still,
it is very hard to compare the performance of these systems as the used
databases often contain copyrighted or private images and are thus not
interchangeable between research groups, also for patient privacy. Most
of the currently used databases for evaluating systems are also fairly
small which is partly due to the high cost in obtaining a gold standard
or ground truth that is necessary for evaluation. Several large image
databases, though without a gold standard, start to be available
publicly, for example by the NIH (National Institutes for Health).
This article describes the creation of a large medical image database
that is used in a teaching file containing more than 8700 varied
medical images. The images are anonymised and can be exchanged free of
charge and copyright. Ground truth (a gold standard) has been obtained
for a set of 26 images being selected as query topics for content-based
query by image example. To reduce the time for the generation of ground
truth, pooling methods well known from the text or information
retrieval field have been used. Such a database is a good starting
point for comparing the current image retrieval systems and to measure
the retrieval quality, especially within the context of teaching files,
image case databases and the support of teaching. For a comparison of
retrieval systems for diagnostic aid, specialised image databases,
including the diagnosis and a case description will need to be made
available, as well, including gold standards for a proper system
evaluation.
A first evaluation event for image retrieval is foreseen at the 2004
CLEF conference (Cross Language Evaluation Forum) to compare text-and
content-based access mechanism to images.},
}