Document Detail


Tracking endocardial motion via multiple model filtering.
MedLine Citation:
PMID:  20501346     Owner:  NLM     Status:  MEDLINE    
Abstract/OtherAbstract:
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.
Authors:
Kumaradevan Punithakumar; Ismail Ben Ayed; Ali Islam; Ian G Ross; Shuo Li
Related Documents :
23021606 - Outcome models in clinical studies: implications for designing and evaluating trials in...
23927696 - Cobrapy: constraints-based reconstruction and analysis for python.
24220986 - Neuroendocrine control of reproduction in lampreys.
24330136 - Guidelines for optimizing design and analysis of clinical studies of nutrient effects.
12085616 - First-order system least squares for elastohydrodynamics with application to flow in co...
16422776 - A systematic review on communicating with patients about evidence.
Publication Detail:
Type:  Journal Article; Research Support, Non-U.S. Gov't     Date:  2010-05-24
Journal Detail:
Title:  IEEE transactions on bio-medical engineering     Volume:  57     ISSN:  1558-2531     ISO Abbreviation:  IEEE Trans Biomed Eng     Publication Date:  2010 Aug 
Date Detail:
Created Date:  2010-07-27     Completed Date:  2010-11-05     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  0012737     Medline TA:  IEEE Trans Biomed Eng     Country:  United States    
Other Details:
Languages:  eng     Pagination:  2001-10     Citation Subset:  IM    
Affiliation:
GE Healthcare, London, ON N6A 4V2, Canada. kumaradevan.punithakumar@ge.com
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Algorithms
Bayes Theorem
Endocardium / physiology*
Humans
Image Processing, Computer-Assisted / methods*
Magnetic Resonance Imaging / methods*
Markov Chains
Movement / physiology*
Normal Distribution
Ventricular Function / physiology

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  Taking side effects into account for HIV medication.
Next Document:  A fuzzy expert system for diabetes decision support application.