Elastic matching of very large digital images on high performance clusters
The aim of the human neuroscanning project is to build an atlas of the human brain, based on a variety of image modalities in particular histological sections of a prepared brain. Reconstructing essential information out of deformed images is a key problem. We describe a method to correct elastic deformations. Since the method is computational expensive a parallel implementation is presented. The measurements and results shown are performed on a cluster of 48 Pentium II PCs connected via Myrinet.
KeywordsPixel Image Outer Loop Parallel Implementation System Load Medical Image Processing
Unable to display preview. Download preview PDF.
- 2.Bajcsy, R., Kovačič, S.: Toward an Individualized Brain Atlas Elastic Matching, MS-CIS-86-71 Grasp Lap 76, Dept. of Computer and Information Science, Moore School, University of Philadelphia (1986)Google Scholar
- 4.Bookstein, F.L.: Size and Shape Spaces for Landmark Data in Two Dimensions, Stat. Sci. 1, (1986) 181–242Google Scholar
- 6.Bro-Nielsen, M.: Medical Image Registration and Surgery Simulation. PhD thesis, IMM, Technical University of Denmark (1996)Google Scholar
- 7.Christensen, G.E.: Deformable Shape Models for Anatomy. PhD thesis, Sever Institute of Technology, Washington University (1994)Google Scholar
- 8.Fischer, B., Modersitzki, J.: Fast Inversion of Matrices Arising in Image Processing. Tech. Report A-98-29, Medical University of Lübeck (1998)Google Scholar
- 11.Obelöer, W., Maehle, E.: Integration of Debugging and Performance Optimization. Proc. 2nd Sino-German Workshop Advanced Parallel Processing Technologies—APPT, 17–24, Koblenz (1997)Google Scholar
- 12.Geist, A, et al.: PVM 3 Users Guide and Reference Manual. Technical Report ORNL/TM-12187, Oak Ridge National Laboratory (1993)Google Scholar
- 13.Medical University of Lübeck, Institute of Computer Engineering, Störtebeker Cluster Project. http://www.iti.mu-luebeck.de/cluster (1998)Google Scholar
- 14.Schormann, T., Henn, S., Zilles, K.: A New Approach to Fast Elastic Alignment with Applications to Human Brains. LNCS Vol. 1131 (1996) 337–342Google Scholar
- 17.Thirion, J.-P.: Non-Rigid Matching Using Demons, in IEEE, Correspondence on Computer Vision and Pattern Recognition, 1996, 245–251Google Scholar