Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

3D registration based on normalized mutual information

Performance of CPU vs. GPU implementation
: Jung, Florian; Wesarg, Stefan

Volltext (PDF; )

Deserno, T.M. ; Gesellschaft für Informatik -GI-, Bonn:
Bildverarbeitung für die Medizin 2010 : Algorithmen - Systeme - Anwendungen; Proceedings des Workshops vom 14. bis 16. März 2010 in Aachen
Berlin: Springer, 2010 (Informatik aktuell)
ISBN: 978-3-642-11967-5
ISSN: 1431-472X
ISSN: 1613-0073
Workshop Bildverarbeitung für die Medizin (BVM) <13, 2010, Aachen>
Konferenzbeitrag, Elektronische Publikation
Fraunhofer IGD ()
parallelization; registration; medical imaging; comparison; Forschungsgruppe Medical Computing (MECO)

Medical image registration is time-consuming but can be sped up employing parallel processing on the GPU. Normalized mutual information (NMI) is a well performing similarity measure for performing multi-modal registration. We present CUDA based solutions for computing NMI on the GPU and compare the results obtained by rigidly registering multi-modal data sets with a CPU based implementation. Our tests with RIRE data sets show a speed-up of factor 5 to 7 for our best GPU implementation.