Independent component analysis: algorithms and applications
Neural Networks
Integrated Image Registration for Cardiac MR Perfusion Data
MICCAI '02 Proceedings of the 5th International Conference on Medical Image Computing and Computer-Assisted Intervention-Part I
Deformation Modelling Based on PLSR for Cardiac Magnetic Resonance Perfusion Imaging
MICCAI '02 Proceedings of the 5th International Conference on Medical Image Computing and Computer-Assisted Intervention-Part I
Evaluation of Rigid and Non-rigid Motion Compensation of Cardiac Perfusion MRI
MICCAI '08 Proceedings of the 11th International Conference on Medical Image Computing and Computer-Assisted Intervention, Part II
Unsupervised Inline Analysis of Cardiac Perfusion MRI
MICCAI '09 Proceedings of the 12th International Conference on Medical Image Computing and Computer-Assisted Intervention: Part II
Hi-index | 0.00 |
This paper presents a novel method for registration of cardiac perfusion MRI. The presented method successfully corrects for breathing motion without any manual interaction using Independent Component Analysis to extract physiologically relevant features together with their time-intensity behavior. A time-varying reference image mimicking intensity changes in the data of interest is computed based on the results of ICA, and used to compute the displacement caused by breathing for each frame. Qualitative and quantitative validation of the method is carried out using 46 clinical quality, short-axis, perfusion MR datasets comprising 100 images each. Validation experiments showed a reduction of the average LV motion from 1.26±0.87 to 0.64±0.46 pixels. Time-intensity curves are also improved after registration with an average error reduced from 2.65±7.89% to 0.87±3.88% between registered data and manual gold standard. We conclude that this fully automatic ICA-based method shows an excellent accuracy, robustness and computation speed, adequate for use in a clinical environment.