Fast spatio-temporal free-form registration of cardiac MR image sequences

  • Authors:
  • Dimitrios Perperidis;Raad Mohiaddin;Daniel Rueckert

  • Affiliations:
  • Visual Information Processing Group, Department of Computing, Imperial College, London, London, United Kingdom;Royal Brompton and Harefield NHS Trust, London, United Kingdom;Visual Information Processing Group, Department of Computing, Imperial College, London, London, United Kingdom

  • Venue:
  • FIMH'05 Proceedings of the Third international conference on Functional Imaging and Modeling of the Heart
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper we present a novel approach to the problem of spatio-temporal alignment of cardiac MR image sequences. This novel method has the ability to correct spatial misalignment caused by global acquisition and local shape differences as well as temporal misalignment caused by differences in the length of the cardiac cycles or by differences in the motion patterns of the hearts. In contrast to our previous approach [1], the algorithm optimizes the spatial and temporal transformation components separately, thus significantly speeding up the registration process. To achieve this we have developed a novel approach for the calculation of the temporal registration which does not require the spatial alignment of the image sequences. The method was evaluated using fifteen cardiac MR image sequences from healthy volunteers and the results were compared to the previously presented method. The results indicate that the performance of the method is similar to the previously presented method [1] while the the computational complexity has been significantly reduced.