Revision of Image 2008: Medical Automatic Image Annotation Task from Tue, 03/25/2008 - 10:25

Following the success of the medical image annotation tasks in 2005, 2006, and 2007 ImageCLEF will offer a medical image annotation task in 2008.

Task Description

The 2008 task will closely follow the protocol of the ImageCLEF 2007 medical image annotation task.

Automatic image annotation or image classification can be an important step when searching for images from a database. Based on the IRMA project a database of 12,089 fully classified radiographs taken randomly from medical routine is made available and can be used to train a classification system. 1,000 radiographs for which classification labels are not available to the participants have to be classified. The aim is to find out how well current techniques can identify image modality, body orientation, body region, and biological system examined based on the images. The results of the classification step can be used for multilingual image annotations as well as for DICOM header corrections.

The difference between this years task and the task of the last year is the distribution of images. To foster using the class hierarchy, the images in the 2008 test set will be mainly from classes which have only few examples of the same class in the training data and thus it will be significantly harder to consider this task as a flat classification task as most of the successful techniques did in 2007. Instead, it is expected that exploiting the hierarchy will lead to large improvments.

The error counting scheme will be the same as in 2007. A description of the error counting scheme is here.

Schedule

Currently we are in the process of checking the data for consistency. As soon as this is done, we will release the training data.

At a later point (tentative: May 15), we will release test images which have to be classified according to the IRMA code hierarchy.
Two weeks later results have to be submitted.

We are trying to have the schedule non-overlapping with the other ImageCLEF tasks to ease participation.

Outline

We will release a dataset of approximately 12,000 images, labelled according to the IRMA code. At a later date, 1,000 test images are released which have to be classified according to the IRMA code. In contrast to past years, this year the test images may have classes that are not fully represented in the training database and thus hierarchical classification techniques will be essential for good performance.

Data Download

DATA IS NOT YET AVAILABLE. YOU CANNOT LOGIN WITH THE CLEF DATA ACCESS ACOUNTS.
Please be a little bit patient. Additional information about data downloads will be provided here shortly.

Organisers

Thomas Deselaers, RWTH Aachen University, Aachen, Germany
Thomas M. Deserno, RWTH Aachen University Hospital, Aachen, Germany