Logo


Medical Image Retrieval Challenge Evaluation

New! ImageCLEF 2008 has begun! The 2008 track protocol has been posted. We have a new database of images obtained from the Goldminer database this year.

New! We have also created a consolidated collection of the images, topics, and relevance judgments from the 2005-2007 running of track. More information is provided below.

ImageCLEFmed is part of the Cross Language Evaluation Forum (CLEF), a benchmarking event for multilingual information retrieval held annually since 2000. CLEF first began as a track in the Text Retrieval Conference (TREC). A multilingual image retrieval track started in 2003, and in 2004 a medical image retrieval track was added. More information about ImageCLEF can be found on its main Web site.

Image or multimedia retrieval is interesting for the domain of cross-language information retrieval as the media such as images are inherently almost insensitive to language. The main goal of ImageCLEFmed is to improve the retrieval of medical images from heterogeneous and multilingual document collections containing images as well as text. Many collections exist on the World Wide Web that contain images as well as multilingual texts. However, the retrieval of images is an often-neglected topic in the information retrieval domain. In particular, hospitals produce an enormous amount of visual data but tools to manage these images and videos are scarce and exist currently only as research prototypes.

Data, Results, and Publications

2008 Track

Consolidated Collection

This collection consists the image collection and topics used in ImageCLEFmed 2005-2007 merged into one single new collection, with relevance judgments done for all topics based on all collections. We ask that any further research done with the collections of 2005-2007 be done with the single consolidated collection. The collection is available to all CLEF participants.

2007 Track

2006 Track

2005 Track

Organizers


             

Sponsors


SIM

Henning Müller
University and Hospitals of Geneva
Geneva, Switzerland
Email:  henning.mueller@sim.hcuge.ch
Web:  http://www.sim.hcuge.ch/medgift/02_Henning_EN.htm

Semantic Mining Semantic Interoperability and Data Mining in Biomedicine
SemanticMining Network of Excellence 507505
OHSU
William Hersh
Oregon Health &Science University
Portland, OR, USA
Email:  hersh@ohsu.edu
Web:  http://www.billhersh.info/
Jayashree Kalpathy-Cramer
Oregon Health &Science University
Portland, OR, USA
Email: kalpathy@ohsu.edu

IST Eurpoean Union Sixth Framework Program
Information Society Technologies
Sheffield
Paul Clough
Sheffield University, UK
Email:  p.d.clough@sheffield.ac.uk
Web:  http://ir.shef.ac.uk/cloughie/

NSF National Science Foundation (U.S.)
Information Technology Research
Grant 0325160





How can I participate in ImageCLEF?

You can register for ImageCLEF by following the links on the CLEF Web site.  Once you have registered and completed the appropriate copyright and declaration forms, you will be able to download the data collections. The data can be downloaded via our FTP server, but if you experience any difficulties or you would rather access the collection via another method (e.g., DVD), please contact Henning Müller.

We have set up two mailing lists, one specific to ImageCLEFmed (contact Bill Hersh to be added) and another for ImageCLEF generally (contact Paul Clough to be added).

Organizing Group

The group below leads the organization of ImageCLEF and are pictured at the CLEF 2005 meeting in Vienna, Austria.

Team

From left to right are:
Last updated - 27 May 2008, William Hersh