Document Detail


Automated segmentation of the left ventricle in cardiac MRI.
MedLine Citation:
PMID:  15450219     Owner:  NLM     Status:  MEDLINE    
Abstract/OtherAbstract:
We present a fully automated deformable model technique for myocardium segmentation in 3D MRI. Loss of signal due to blood flow, partial volume effects and significant variation of surface grey value appearance make this a difficult problem. We integrate various sources of prior knowledge learned from annotated image data into a deformable model. Inter-individual shape variation is represented by a statistical point distribution model, and the spatial relationship of the epi- and endocardium is modeled by adapting two coupled triangular surface meshes. To robustly accommodate variation of grey value appearance around the myocardiac surface, a prior parametric spatially varying feature model is established by classification of grey value surface profiles. Quantitative validation of 121 3D MRI datasets in end-diastolic (end-systolic) phase demonstrates accuracy and robustness, with 2.45 mm (2.84 mm) mean deviation from manual segmentation.
Authors:
Michael R Kaus; Jens von Berg; Jürgen Weese; Wiro Niessen; Vladimir Pekar
Related Documents :
21717489 - The impact of selection bias on test decisions in randomized clinical trials.
17282889 - Model-based graph cut method for segmentation of the left ventricle.
10149889 - Utility and limitations of linear models for echocardiographic estimation of left ventr...
25346699 - The addict in us all.
21767719 - A predictive model to help identify intimate partner violence based on diagnoses and ph...
22021089 - A clinically applicable six-segmented foot model.
25382889 - A unified discontinuous galerkin framework for time integration.
6422839 - A semantic differential for external comparison of conceptual nursing models.
21868949 - Derivatives of tree sets with applications to grammatical inference.
Publication Detail:
Type:  Journal Article    
Journal Detail:
Title:  Medical image analysis     Volume:  8     ISSN:  1361-8415     ISO Abbreviation:  Med Image Anal     Publication Date:  2004 Sep 
Date Detail:
Created Date:  2004-09-28     Completed Date:  2004-12-02     Revised Date:  2005-06-07    
Medline Journal Info:
Nlm Unique ID:  9713490     Medline TA:  Med Image Anal     Country:  England    
Other Details:
Languages:  eng     Pagination:  245-54     Citation Subset:  IM    
Affiliation:
Philips Research Laboratories, Sector Technical Systems, Röntgenstr. 24-26, D-22335 Hamburg, Germany. michael.kaus@philips.com
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Algorithms*
Automation
Humans
Image Processing, Computer-Assisted / methods*
Imaging, Three-Dimensional
Magnetic Resonance Imaging*
Ventricular Dysfunction, Left / diagnosis*

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


Previous Document:  Region segmentation using information divergence measures.
Next Document:  Segmentation of 4D cardiac MR images using a probabilistic atlas and the EM algorithm.