IRMA (Image Retrieval in Medical Applications) 
 
IRMA
Image Retrieval in
Medical Applications
  
  
 Open Area 
 
 - Contact 
 - Project Description 
 - Involved Institutes 
 - Involved Scientists 
 - Former Scientists 
 - Publications 
 - Conference Presentations 
 - Papers on IRMA data 
 - Student Projects 
 - Open Positions 
 - Open Projects 
 - Online Demos 
 - IRMA-Code download 
 - Downloads 
 - Institutes with IRMA data 
 - BVM 2010 Gallery  
 - Acknowledgements 
  
 Internal Area 
 
 - Login 
 
 
 
Gefördert durch die DFG
Le 1108/4
Le 1108/6
De 1563/9

 

Datasets for non-commercial download

 Search results: 0

Search:
10.000 IRMA images of 57 categories
for ImageCLEFmed 2005
sample images

Authors:

Lehmann TM, Schubert H, Ott B, Leisten M

Release: V1.0 , 2005

Remark:

On this page, you can access data that has been used in several scientific studies. In order to make the results comparable, these datasets are available for other non-commercial evaluations. The non-commercial purpose must be explicitly acknowledged using the prepared transfer agreement form. To receive your individual account, please complete the form, print it onto official stationary of your department, and send us the signed document.

Description:

This collection compiles anonymous radiographs, which have been arbitrarly selected from routine at the Department of Diagnostic Radiology, Aachen University of Technology (RWTH), Aachen, Germany. The imagery represents different ages, genders, view positions and pathologies. Therefore, image quality varies significantly. All images were downscaled to fit into a 512 x 512 bounding box maintaining the original aspect ratio. All images were classified according to the IRMA code. Based on this code, 57 categories were defined. For 9000 images, these categories are transparent by the name of the folder. The remaining 1000 images without code are used as test data for the ImageCLEFmed 2005 competition.

  • Training data: 9000 radiographs in 57 categories.
  • Test data: 1000 radiographs without classification.
  • Category names: medical terms characterizing the 57 categories in German and English languages.

References:

The data has been used in several investigations. Please refer to the papers which are listed below. They are available in pdf-format via the menu Publications on the left.

  • Proceedings CLEF 2005, in press.
  • Proceedings SPIE 2003; 5033: 440-451.
    Description of IRMA code

Downloads:

 
 Top
© 2002/03 IRMA