Construction of a statistical model for cardiac motion analysis using nonrigid image registration

Inf Process Med Imaging. 2003 Jul:18:599-610. doi: 10.1007/978-3-540-45087-0_50.

Abstract

In this paper we present a new technique for tracking the movement of the myocardium using a statistical model derived from the motion fields in the hearts of several healthy volunteers. To build the statistical model we tracked the motion of the myocardium in 17 volunteers using a nonrigid registration technique based on free-form deformations and mapped the motion fields obtained into a common reference coordinate system. A principal component analysis (PCA) was then performed on the motion fields to extract the major modes of variation in the fields between the successive time frames. The modes of variation obtained were then used to parametrize the free-form deformations and build our statistical model. The results of using our model to track the motion of the heart in normal volunteers are also presented.

Publication types

  • Clinical Trial
  • Comparative Study
  • Validation Study

MeSH terms

  • Algorithms*
  • Computer Simulation
  • Heart / anatomy & histology*
  • Heart / physiology*
  • Humans
  • Image Enhancement / methods
  • Image Interpretation, Computer-Assisted / methods*
  • Imaging, Three-Dimensional / methods
  • Magnetic Resonance Imaging
  • Male
  • Models, Cardiovascular*
  • Models, Statistical
  • Movement / physiology*
  • Pattern Recognition, Automated
  • Principal Component Analysis
  • Reproducibility of Results
  • Sensitivity and Specificity
  • Subtraction Technique*