home  |   research   |  members   |  projects  |  publications   |  conferences of interest   |  downloads   |  contact  |  intern
 
 

Project Description

This is "The Multimedia Signal Processing and Security Lab", short WaveLab, website. We are a research group at the Computer Sciences Department of the University of Salzburg headed by Andreas Uhl. The short name "WaveLab" already indicates that wavelets are among our favorite tools - we have 15 years of experience in this area. Our research is focused on Multimedia Security including Watermarking, Image and Video Compression, Medical Image Classification, and Biometrics.
   

Computer Assisted Mucosal Lesion Analysis in High Definition Digital Chromoendoscopic Colon Images Using Wavelet Techniques (ColonHD)

 

Project Description:

ColonHD (FWF TRP project 206) is a joint project with Michael Häfner from the St. Elisabeth Hospital, Vienna. The aim of the project is to develop a computer-based decision support system for an automated diagnosis of colon cancer based on high-definition digital chromoendoscopic colon imagery. Staging is done according to a histopathologic ground truth. Images and videos as acquired in Vienna are transfered to Salzburg in anonymous fashion. The Salzburg branch is developing custom classification techniques based on various incarnations of the wavelet transform where the aim is to achieve equivalent classification results as compared to the histological findings.

 
 

Members:

 
 

Timeframe:

  • June 2011 - December 2013
 
 

Publications:

  1. [Ribeiro16d ] Exploring Texture Transfer Learning for Colonic Polyp Classification via Convolutional Neural Networks E. Ribeiro, M. Häfner, G. Wimmer, T. Tamaki, J.J.W. Tischendorf, S. Yoshida, S. Tanaka, A. Uhl In 14th International IEEE Symposium on Biomedical Imaging (ISBI'17)April 2017, accepted
  2. [Wimmer16d ] Evaluation of i-Scan Virtual Chromoendoscopy and Traditional Chromoendoscopy for the Automated Diagnosis of Colonic Polyp G. Wimmer, M. Gadermayr, R. Kwitt, A. Häfner, D. Merhof, A. Uhl In Proceedings of the 3rd International Workshop on Computer-Assisted and Robotic Endoscopy (CARE), pp. 59-71, Springer LNCS, 10170, 2016
  3. [Wimmer16c ] A novel Filterbank especially designed for the Classification of Colonic Polyps G. Wimmer, A. Vecsei, A. Uhl In Proceedings of the 23rd International Conference on pattern Recognition (ICPR)2016, accepted
  4. [Wimmer16a  ] Directional Wavelet based Features for Colonic Polyp Classification Georg Wimmer, Toru Tamaki, J.J.W. Tischendorf, Michael Häfner, Shinji Tanaka, Shigeto Yoshida, Andreas Uhl Medical Image Analysis 31, pp. 16-36, 2016
  5. [Ribeiro16c  ] Exploring Deep Learning and Transfer Learning for Colonic Polyp Classification E. Ribeiro, A. Uhl, G. Wimmer, M. Häfner Computational and Mathematical Methods in Medicine 2016, pp. Article ID 6584725, Hindawi Publishing Corporation, 2016
  6. [Liedlgruber16b ] Texture description using Dual Tree Complex Wavelet Packets M. Liedlgruber, M. Häfner, J. Hämmerle-Uhl, A. Uhl In Advances in Multimedia Information Processing -- Proceedings of the 17th Pacific-Rim Conference on Multimedia (PCM'16), pp. 181-190, Xi'an, China, Springer LNCS, 9916, September 15 - September 16
  7. [Ribeiro16b ] Transfer Learning for Colonic Polyp Classification using Off-the-Shelf CNN Features (Best Paper Award, 3rd Place) E. Ribeiro, A. Uhl, G. Wimmer, M. Häfner In Proceedings of the 3rd International Workshop on Computer-Assisted and Robotic Endoscopy (CARE'16), pp. 1-13, Springer LNCS, 10170, 2016
  8. [Elmer15c ] Impact of Lossy Image Compression on CAD Support Systems for Colonoscopy Peter Elmer, Michael Häfner, Toru Tamaki, Shinji Tanaka, Rene Thaler, Andreas Uhl, Shigeto Yoshida In Computer-Assisted and Robotic Endoscopy (CARE'15), pp. 1-11, Springer Lecture Notes in Computer Science, 9515, Oct. 2016
  9. [Ribeiro16a ] Colonic Polyp Classification with Convolutional Neural Networks Eduardo Ribeiro, Andreas Uhl, Michael Häfner In Proceedings of the 29th IEEE International Symposium on Computer-Based Medical Systems (CBMS'16), pp. 253-258, June 2016
  10. [Elmer16a ] Compression-scenarios for LIRE-based CBIR on colonoscopy data Peter Elmer, Michael Häfner, Toru Tamaki, Shinji Tanaka, Rene Thaler, Andreas Uhl, Shigeto Yoshida In Proceedings of Bildverarbeitung für die Medizin 2016 (BVM'16), pp. 152-157, Springer Informatik Aktuell, March 2016
  11. [Haefner15b  ] Local Fractal Dimension based approaches for Colonic Polyp Classification Michael Häfner, Toru Tamaki, Shinji Tanaka, Andreas Uhl, Georg Wimmer, Shigeto Yoshida Medical Image Analysis 26, pp. 92-107, 2015
  12. [Uhl14a  ] A systematic evaluation of the scale invariance of texture recognition methods Andreas Uhl, Georg Wimmer Pattern Analysis and Applications 18, pp. 945-969, Springer London, 2015
  13. [Haefner15a ] Colonic Polyp Classification in High- Definition Video Using Complex Wavelet-Packets Michael Häfner, Michael Liedlgruber, Andreas Uhl In Proceedings of Bildverarbeitung für die Medizin 2015 (BVM'15), pp. 365-370, March 2015
  14. [Haefner13c  ] A Novel Shape Feature Descriptor for the Classification of Polyps in HD Colonoscopy A. Häfner, A. Uhl, G. Wimmer In Medical Computer Vision. Large Data in Medical Imaging (Proceedings of the 3rd International MICCAI - MCV Workshop 2013), pp. 205-213, Springer LNCS, 8331, 2014
  15. [Haefner14b  ] Bridging the Resolution Gap Between Endoscope Types for a Colonic Polyp Classification M. Häfner, M. Liedlgruber, A. Uhl, G. Wimmer In Proceedings of the 22nd International Conference on Pattern Recognition (ICPR'14), pp. 2739-2744, 2014
  16. [Haefner14c  ] Evaluation of Super-Resolution Methods in the Context of Colonic Polyp Classification M. Häfner, M. Liedlgruber, A. Uhl, G. Wimmer In Proceedings of the 12th International Workshop on Content-Based Multimedia Indexing (CBMI'14), pp. 1-6, 2014
  17. [Haefner14d  ] Shape and Size Adapted Local Fractal Dimension for the Classification of Polyps in HD colonoscopy M. Häfner, A. Uhl, G. Wimmer In Proceedings of the IEEE International Conference on Image Processing 2014 (ICIP'14)Oct. 2014
  18. [Haefner14a  ] Comparison of Super-Resolution Methods for HD-Video Endoscopy M. Häfner, M. Liedlgruber, A. Uhl In Proceedings of Bildverarbeitung für die Medizin 2014 (BVM'14), pp. 78-83, Aachen, Germany, Springer Informatik aktuell, March 2014
  19. [Haefner13b  ] Super-Resolution Techniques Evaluated in the Context of HD Endoscopic Imaging M. Häfner, M. Liedlgruber, A. Uhl Department of Computer Sciences, University of Salzburg, Austriahttp://www.cosy.sbg.ac.at/tr, Technical Report 2013-04, 2013
  20. [Hegenbart13a   ] Scale invariant texture descriptors for classifying celiac disease Sebastian Hegenbart, Andreas Uhl, Andreas Vécsei, Georg Wimmer Medical Image Analysis 17:4, pp. 458-474, 2013
  21. [Haefner13a  ] POCS-based Super-Resolution for HD Endoscopy Video Frames M. Häfner, M. Liedlgruber, A. Uhl In Proceedings of the 26th IEEE International Symposium on Computer-Based Medical Systems (CBMS'13), pp. 185-190, June 2013
  22. [Liedlgruber11e  ] Computer-aided Decision Support Systems for Endoscopy in the Gastrointestinal Tract: A Review Michael Liedlgruber, Andreas Uhl IEEE Reviews in Biomedical Engineering 4, pp. 73-88, 2012
  23. [Haefner12a  ] Delaunay Triangulation-based Pit Density Estimation for the Classification of Polyps in High-magnification Chromo-colonoscopy M. Häfner, M. Liedlgruber, A. Uhl, A. Vécsei, F. Wrba Computer Methods and Programs in Biomedicine 107:3, pp. 565-581, 2012
  24. [Hegenbart12b  ] Customised Frequency Pre-filtering in a Local Binary Pattern-Based Classification of Gastrointestinal Images Sebastian Hegenbart, Stefan Maimone, Andreas Uhl, Andreas Vécsei, Georg Wimmer In Medical Content-Based Retrieval for Clinical Decision Support, pp. 99-109, Springer Lecture Notes in Computer Science, 7723, Oct. 2012
  25. [Haefner12b  ] Evaluation of Cross-validation Protocols for the Classification of Endoscopic Images of Colonic Polyps M. Häfner, M. Liedlgruber, S. Maimone, A. Uhl, A. Vécsei, F. Wrba In Proceedings of the 25th IEEE International Symposium on Computer-Based Medical Systems (CBMS'12)June 2012