Document Detail


Organ Pose Distribution Model and an MAP Framework for Automated Abdominal Multi-Organ Localization.
MedLine Citation:
PMID:  21173865     Owner:  NLM     Status:  Publisher    
Abstract/OtherAbstract:
Abdominal organ localization is required as an initialization step for most automated abdominal organ analysis tasks, i.e. segmentation, registration, and computer aided-diagnosis. Automated abdominal organ localization is difficult because of the large variability of organ shapes, similar appearances of different organs in images, and organs in close proximity to each other. Previous methods predicted only the organ locations, but not the full organ poses including additionally sizes and orientations. Thus they were often not accurate enough to initialize other image analysis tasks. In this work we proposed a maximum a posteriori (MAP) framework to estimate the poses of multiple abdominal organs from non-contrast CT images. A novel organ pose distribution model is proposed to model the organ poses and limit the search space. Additionally the method uses probabilistic atlases for organ shapes, and Gaussian mixture models for organ intensity profile. An MAP problem is then formulated and solved for organ poses. The method was applied for the localization of liver, left and right kidneys, spleen, and pancreas, and showed promising results, especially on liver and spleen (with mean location and orientation errors under 5.3 mm and 7 degrees respectively).
Authors:
Xiaofeng Liu; Marius George Linguraru; Jianhua Yao; Ronald M Summers
Related Documents :
21384325 - The life of form: emergent patterns of morphological transformation.
2244635 - The déjà vu experience: remembrance of things past?
19412735 - Multi-marker strategies in heart failure: clinical and statistical approaches.
21430725 - In defence of inclusive fitness theory.
17484775 - Assessing the adequacy of variance function in heteroscedastic regression models.
20033445 - Arabidopsis thaliana as a model for functional nectary analysis.
Publication Detail:
Type:  JOURNAL ARTICLE    
Journal Detail:
Title:  Lecture notes in computer science     Volume:  6326     ISSN:  0302-9743     ISO Abbreviation:  -     Publication Date:  2010 Jan 
Date Detail:
Created Date:  2010-12-21     Completed Date:  -     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  101302926     Medline TA:  Lect Notes Comput Sci     Country:  -    
Other Details:
Languages:  ENG     Pagination:  393-402     Citation Subset:  -    
Affiliation:
Imaging Biomarkers and Computer Aided Diagnosis Laboratory, Radiology and Imaging Sciences, Clinical Center, National Institutes of Health, Bethesda, MD 20892.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Grant Support
ID/Acronym/Agency:
NIH0013146007//PHS HHS; ZIA CL040004-08//CLC NIH HHS

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


Previous Document:  Unmasking the acoustic effects of vowel-to-vowel coarticulation: A statistical modeling approach.
Next Document:  Lensfree color imaging on a nanostructured chip using compressive decoding.