Home
Uni-Logo
 

BIOSS - 3D and 4D Image Analysis for the 4D-Analyser (DFG)


Project Members


Introduction

Official BIOSS website

Bioss Research Areas

Universal Image Analysis (for the BIOSS 4D-Analyser)




The goal of the project "D2-1 Universal Image Analysis" is to provide universal image analysis modules for the 4D Analyser. These modules will be "plugged together" to extract the biologically relevant quantitative parameters from the huge amount of recorded 3D/4D data, and to provide decisions for an automated manipulation of the experiments. One unique feature of our modules will be the adaption of a module to the specific application just by (interactive) training instead of tedious manual parameter adjustment. Further goals are an integrated, easy to understand, but powerful data and module management, which allows an efficient development for the computer scientists, and at the same time an easy and intuitive usage for the end-user. The goal for all modules is to reach a full automation, such that high-throughput experiments become possible. The modules are split into four categories:
  1. Modules for the extraction of anatomy / anatomical references provide anatomical and functional coordinate systems.
  2. Modules for the description of marker patterns provide features and statistical descriptions relative to the anatomy and invariant or robust to known variations.
  3. Modules for data pre-processing improve the raw data quality, e.g., by using multiple recordings and physical models.
  4. Modules for data interpretation provide classifications, statistical descriptions, comparison of populations, and decisions for automated experiments.


Publications

[1] M. Reisert and H. Burkhardt. Complex derivative filters. IEEE Transactions on Image Processing, 17(12):2265-2274, 2008.
[2] Qing Wang, Olaf Ronneberger, and Hans Burkhardt. Rotational invariance based on fourier analysis in polar and spherical coordinates. IEEE Transactions on Pattern Analysis and Machine Intelligence, 31:1715-1722, 2009.
[ .pdf ]
[3] M. Emmenlauer, O. Ronneberger, A. Ponti, P. Schwarb, A. Griffa, A. Filippi, R. Nitschke, W. Driever, and H. Burkhardt. Xuvtools: free, fast and reliable stitching of large 3d datasets. Journal of Microscopy, 233(1):42-60, 2009.
[ .pdf ]
[4] R. Bensch, O. Ronnerberger, B. Greese, C. Fleck, K. Wester, M. Hülskamp, and H. Burkhardt. Image analysis of arabidopsis trichome patterning in 4d confocal datasets. In Biomedical Imaging: From Nano to Macro, 2009. ISBI 2009. 6th IEEE International Symposium on, pages 742-745, 2009.
[ .pdf ]
[5] Maja Temerinac-Ott and Hans Burkhardt. Multichannel image restoration based on optimization of the structural similarity index. In Asilomar Conference on Signals, Systems, and Computers, nov 2009.
[ .pdf ]
[6] Q. Wang, O. Ronneberger, E. Schulze, R. Baumeister, and H. Burkhardt. Using lateral coupled snakes for modeling the contours of worms. In Proceedings of the DAGM 2009, LNCS, pages 542-551, Jena, Germany, 2009. Springer.
[7] Margret Keuper, Jan Padeken, Patrick Heun, Hans Burkhardt, and Olaf Ronneberger. A 3d active surface model for the accurate segmentation of drosophila schneider cell nuclei and nucleoli. In Advances in Visual Computing. Proceedings of the 5th International Symposium on Visual Computing, ISVC 2009, Part I, volume 5875 of Lecture Notes in Computer Science, pages 865-874. Springer, 2009.
[ http | .pdf ]
[8] Maja Temerinac, Margret Keuper, and Hans Burkhardt. Evaluation of a new point clouds registration method based on group averaging features. In Proceedings of 20th International Conference on Pattern Recognition (ICPR 2010), Istanbul, Turkey, 2010. (accepted).
[9] M. Keuper, T. Schmidt, J. Padeken, P. Heun, K. Palme, H. Burkhardt, and O. Ronneberger. 3d deformable surfaces with locally self-adjusting parameters - a robust method to determine cell nucleus shapes. In Proceedings of the 20th International Conference on Pattern Recognition (ICPR 2010), Istanbul, Turkey, 2010. accepted.
[10] M. Keuper, J. Padeken, P. Heun, H. Burkhardt, and O. Ronneberger. Mean shift gradient vector flow: A robust external force field for 3d active surfaces. In Proceedings of the 20th International Conference on Pattern Recognition (ICPR 2010), Istanbul, Turkey, 2010. accepted.
[11] M Schlachter, M Reisert, C Herz, F Schluermann, S Lassmann, M Werner, H Burkhardt, and O Ronneberger. Harmonic filters for 3d multi-channel data: Rotation invariant detection of mitoses in colorectal cancer. Medical Imaging, IEEE Transactions on, PP(nn):nn, 2010. accepted for Publication.
[12] Dorothee Saur, Olaf Ronneberger, Dorothee Kummerer, Irina Mader, Cornelius Weiller, and Stefan Kloppel. Early functional magnetic resonance imaging activations predict language outcome after stroke. Brain, 133(4):1252-1264, 2010.
[13] Margret Keuper, Robert Bensch, Karsten Voigt, Alexander Dovzhenko, Klaus Palme, Hans Burkhardt, and Olaf Ronneberger. Semi-supervised learning of edge filters for volumetric image segmentation. In Proceedings of the DAGM 2010, LNCS, page nn, Darmstadt, Germany, 2010. Springer. to appear.
[14] Soeren Lienkamp, Athina Ganner, Christopher Boehlke, Thorsten Schmidt, Sebastian J. Arnold, Tobias Schäfer, Daniel Romaker, Julia Schuler, Sylvia Hoff, Christian Powelske, Annekathrin Eifler, Corinna Krönig, Axel Bullerkotte, Roland Nitschke, E. Wolfgang Kuehn, Emily Kim, Hans Burkhardt, Thomas Brox, Olaf Ronneberger, Joachim Gloy, and Gerd Walz. Inversin relays frizzled-8 signals to promote proximal pronephros development. Proceedings of the National Academy of Sciences, 107(47):20388-20393, 2010.

Demos and Tools

  • libsvmtl -- a Support Vector Machine Template Library
  • XuvTools -- eXtend yoUr View Toolkit (stitching of large 3D datasets)