Related Experiment Video
Updated: Jul 9, 2026
07:21
Magnetic Resonance Derived Myocardial Strain Assessment Using Feature Tracking
Published on: February 12, 2011
Predictive K-PLSR myocardial contractility modeling with phase contrast MR velocity mapping
Su-Lin Lee1, Qian Wu, Andrew Huntbatch
1Institute of Biomedical Engineering, Imperial College London, UK. su-lin.lee@imperial.ac.uk
Medical Image Computing and Computer-Assisted Intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
|November 30, 2007
Summary
This study introduces a new predictive motion modeling scheme using Kernel-Partial Least Squares Regression (K-PLSR) for cardiac magnetic resonance (CMR) imaging. This method enhances myocardial contractility analysis by improving virtual tagging efficiency and accuracy.
Area of Science:
- Cardiovascular Imaging
- Biomedical Engineering
- Computational Modeling
Background:
- Cardiac magnetic resonance (CMR) imaging offers advanced insights into myocardial contractility.
- Virtual tagging frameworks visualize localized myocardial deformation using phase contrast velocity mapping.
- Subject-specific modeling requires integrating structural and functional cardiac data.
Purpose of the Study:
- To evaluate a non-linear Kernel-Partial Least Squares Regression (K-PLSR) predictive motion modeling scheme.
- To apply this scheme within the virtual tagging framework for CMR.
- To enhance the analysis of myocardial contractility.
Main Methods:
- Developed a K-PLSR method to create a compact, non-linear deformation model.
- Predicted the entire deformation field using a limited set of control points.
- Integrated the K-PLSR model with virtual tagging to guide mesh refinement based on coarse grid motion.
Main Results:
- The K-PLSR predictive motion modeling significantly reduced the search space for virtual tagging.
- Achieved increased convergence speed in the algorithm.
- Demonstrated effectiveness and numerical accuracy using simulated data and in vivo CMR velocity mapping from 7 subjects.
Conclusions:
- The proposed K-PLSR technique offers advantages over conventional mesh refinement in CMR.
- This method improves the predictive accuracy and efficiency of myocardial contractility analysis.
- Brings advanced CMR myocardial contractility analysis closer to clinical application.
