Fast Registration of Cardiac Perfusion MRI

Mikkel B. Stegmann, Henrik B. W. Larsson

AbstractThis abstract presents a novel method for registration of cardiac perfusion MRI sequences. By performing complex analyses of variance and clustering in an annotated training set off-line, our method provides real-time segmentation in an on-line setting. This renders the method feasible for live motion-compensation in MR scanners. Changes in image intensity during the bolus passage are modelled by an Active Appearance Model augmented with a cluster analysis of the training set. Preliminary validation carried out using five subjects showed acceptable segmentation accuracy produced very rapidly (below 40 ms per image).
TypeConference paper [Abstract]
ConferenceProc. International Society of Magnetic Resonance In Medicine - ISMRM 2003, Toronto, Ontario, Canada
Year2003    Month May    pp. 702
AddressBerkeley, CA, USA
Electronic version(s)[pdf]
BibTeX data [bibtex]
IMM Group(s)Image Analysis & Computer Graphics