UnivIS
Information system of Friedrich-Alexander-University Erlangen-Nuremberg © Config eG 
FAU Logo
  Collection/class schedule    module collection Home  |  Legal Matters  |  Contact  |  Help    
search:      semester:   
 Lectures   Staff/
Facilities
   Room
directory
   Research-
report
   Publications   Internat.
contacts
   Thesis
offers
   Phone
book
 
 
 Layout
 
printable version

 
 
Departments >> Faculty of Engineering >> Department of Computer Science >> Chair of Computer Science 5 (Pattern Recognition) >>
MEDICO – Towards Scalable Semantic Image Search in Medicine

The Medico project is part of the THESEUS research program initiated by the Federal Ministry of Economics and Technology (BMWi). Medico was proposed by an industry-led consortium in August 2006, accepted by the BWMi and started in August 2007. The BMWi granted 90 Mio EUR to THESEUS over five years.
The vision of the Medico project is to provide semantic access to medical image databases. The idea is to automatically generate formal descriptions of medical images. A user can then search those descriptions by providing query keywords or a query image. When a query image is used, it is automatically decomposed and keywords are generated from its formal description which are used for the search.
To achieve this vision, several sub-problems have to be solved:
  • The robust hierarchical decomposition and understanding of medical images

  • Development of a new scalable and hierarchical information representation

  • Development of new architectures that support semantic image search and scalable searching solutions.

The potential for intelligent image search engines for the medical domain is huge:

  • Future clinicians will be able to search and access image databases based on content and semantics, thus receiving point-of-care decision support.

  • CAD (Computer Aided Detection) technologies will benefit by operating at the higher, semantic level, hence shortening the time-to-market interval.

  • Patient recruitment for clinical trials could be implemented in a straightforward manner by searching the image content.

  • Epidemiological studies could be pursued by searching geographically distributed image databases.

Project manager:
Dr. Martin Huber, Prof. Dr.-Ing. Joachim Hornegger

Project participants:
Dr.-Ing. Johannes Feulner, Dipl.-Ing. Ingmar Voigt

Keywords:
Semantic Search; Image Understanding; Medical Image Processing

Duration: 1.8.2007 - 31.7.2012

Sponsored by:
Siemens

Contact:
Feulner, Johannes
E-Mail: johannes.feulner@informatik.uni-erlangen.de
Publications
Feulner, Johannes ; Zhou, S. Kevin ; Seifert, Sascha ; Cavallaro, Alexander ; Hornegger, Joachim ; Comaniciu, Dorin: Estimating the Body Portion of CT Volumes by Matching Histograms of Visual Words. In: Pluim, Josien P. W. ; Dawant, Benoit M. (Ed.) : Proceedings of the SPIE (Medical Imaging 2009: Image Processing Orlando 7-12.2.2009). 2009, pp 72591V.
Feulner, Johannes ; Zhou, S. Kevin ; Cavallaro, Alexander ; Seifert, Sascha ; Hornegger, Joachim ; Comaniciu, Dorin: Fast Automatic Segmentation of the Esophagus from 3D CT data using a Probabilistic Model. In: Yang, Guang-Zhong ; Hawkes, David ; Rueckert, Daniel ; Noble, Alison ; Taylor, Chris (Ed.) : Lecture Notes in Computer Science, LNCS (MICCAI London (UK) 23.09.2009). Vol. 5761. Berlin : Springer, 2009, pp 255-262.
Seifert, Sascha ; Barbu, Adrian ; Zhou, S. Kevin ; Liu, David ; Feulner, Johannes ; Huber, Martin ; Sühling, Michael ; Cavallaro, Alexander ; Comaniciu, Dorin: Hierarchical parsing and semantic navigation of full body CT data. In: Pluim, Josien P. W. ; Dawant, Benoit M. (Ed.) : Proceedings of the SPIE (Medical Imaging 2009: Image Processing Orlando 7-12.2.2009). 2009, pp 725902.
Ionasec, Razvan Ioan ; Voigt, Ingmar ; Georgescu, Bogdan ; Wang, Yang ; Houle, Helene ; Hornegger, Joachim ; Navab, Nassir ; Comaniciu, Dorin: Personalized Modeling and Assessment of the Aortic-Mitral Coupling from 4D TEE and CT. In: Guang-Zhong, Yang ; David, Hawkes ; Daniel, Rueckert ; Alison, Noble ; Chris ,Taylor (Ed.) : Proceedings of 12th International Conference on Medical Image Computing and Computer Assisted Intervention 2009 (MICCAI 2009 London (UK) 21.-23.09.2009). Heidelberg : Springer, 2009, pp 767-775. (Lecture Notes in Computer Science Vol. 5762) - ISBN 978-3-642-04267-6
Voigt, Ingmar ; Vitanovski, Dime ; Ionasec, Razvan Ioan ; Tsymbal, Alexey ; Georgescu, Bogdan ; Zhou, Shaohua Kevin ; Huber, Martin ; Navab, Nassir ; Hornegger, Joachim ; Comaniciu, Dorin: Learning discriminative distance functions for valve retrieval and improved decision support in valvular heart disease. In: Haynor, David R. ; Dawant, Benoit M. (Ed.) : Proceedings of SPIE Medical Imaging 2010 (SPIE Medical Imaging 2010 San Diego, CA, USA 12.-17.02.2010). Bellingham, WA, USA : SPIE, 2010, pp no pagination.
UnivIS is a product of Config eG, Buckenhof