Number of the records: 1
Elastic registration of biomedical images on CUDA-Supported graphics procesor units
- 1.
SYSNO ASEP 0347031 Document Type C - Proceedings Paper (int. conf.) R&D Document Type Conference Paper Title Elastic registration of biomedical images on CUDA-Supported graphics procesor units Author(s) Michálek, Jan (FGU-C) RID
Čapek, Martin (FGU-C) RID, ORCID
Janáček, Jiří (FGU-C) RID, ORCID
Kubínová, Lucie (FGU-C) RID, ORCIDSource Title Analysis of biomedical signals and images. - Brno : University of technology, 2010 - ISSN 1211-412X - ISBN 978-80-214-4106-4 Pages s. 43-48 Number of pages 6 s. Action International EURASIP Conference Biosignal /20./ Event date 27.06.2010-29.06.2010 VEvent location Brno Country CZ - Czech Republic Event type WRD Language eng - English Country CZ - Czech Republic Keywords volume reconstruction ; elastic alignment ; CUDA Subject RIV JD - Computer Applications, Robotics R&D Projects LC06063 GA MŠMT - Ministry of Education, Youth and Sports (MEYS) GA102/08/0691 GA ČR - Czech Science Foundation (CSF) GA304/09/0733 GA ČR - Czech Science Foundation (CSF) CEZ AV0Z50110509 - FGU-C (2005-2011) UT WOS 000303723700007 Annotation Elastic registration is a task of finding the matching of two images, using geometric and elastic transformations, so that objects in images have the same size, position and orientation. We apply elastic registration in the framework of volume reconstruction, where an object acquired from parallel physical sections is composed and mutual positions of the sections including deformations caused by their cutting have to be found. The method lies in optimizing a functional consisting of two parts: first, discrete total variation as a measure of roughness and, second, L1 norm as a measure of dissimilarity of images. As a parallelizable optimization strategy we apply a potential-based equivalent transformation of a (max,+)-labelling problem. CUDA-based implementation of the described elastic registration algorithm is reasonably fast, requires seconds to minutes of calculations, provides good results and, thus, can be used for practical tasks dealing with alignment of biomedical images Workplace Institute of Physiology Contact Lucie Trajhanová, lucie.trajhanova@fgu.cas.cz, Tel.: 241 062 400 Year of Publishing 2011
Number of the records: 1