Title :
Tracking Endocardial Motion Via Multiple Model Filtering
Author :
Punithakumar, Kumaradevan ; Ben Ayed, Ismail ; Islam, Ali ; Ross, Ian G. ; Li, Shuo
Author_Institution :
GE Healthcare, London, ON, Canada
Abstract :
Tracking heart motion plays an essential role in the diagnosis of cardiovascular diseases. As such, accurate characterization of dynamic behavior of the left ventricle (LV) is essential in order to enhance the performance of motion estimation. However, a single Markovian model is not sufficient due to the substantial variability in typical heart motion. Moreover, dynamics of an abnormal heart could be very different from that of a normal heart. This study introduces a tracking approach based on multiple models, each matched to a different phase of the LV motion. First, the algorithm adopts a graph cut distribution matching method to tackle the problem of segmenting LV cavity from cardiac MR images, which is acknowledged as a difficult problem because of low contrast and photometric similarities between the heart wall and papillary muscles within the LV cavity. Second, interacting multiple model (IMM), an effective estimation algorithm for Markovian switching system, is devised subsequent to the segmentations to yield state estimates of the endocardial boundary points. The IMM also yields the model probability indicating the model that most closely matches the LV motion. The proposed method is evaluated quantitatively by comparison with independent manual segmentations over 2280 images acquired from 20 subjects, which demonstrated competitive results in comparisons with related recent methods.
Keywords :
belief networks; biomedical MRI; cardiology; image segmentation; medical image processing; tracking filters; IMM; Markovian switching systems; cardiac MR images; endocardial boundary points; graph cut distribution matching method; heart wall; image segmentation; interacting multiple model; left ventricle dynamic behavior; multiple model filtering; papillary muscles; recursive Bayesian filtering; tracking endocardial motion; Cardiac wall motion estimation; MRI; Markovian switching systems; interacting multiple model (IMM) algorithm; recursive Bayesian filtering; Algorithms; Bayes Theorem; Endocardium; Humans; Image Processing, Computer-Assisted; Magnetic Resonance Imaging; Markov Chains; Movement; Normal Distribution; Ventricular Function;
Journal_Title :
Biomedical Engineering, IEEE Transactions on
DOI :
10.1109/TBME.2010.2048752