| Multilevel segmentation and integrated bayesian model classification with an application to brain tumor segmentation. | |
| | |
MedLine Citation:
|
PMID: 17354845 Owner: NLM Status: MEDLINE |
Abstract/OtherAbstract:
|
We present a new method for automatic segmentation of heterogeneous image data, which is very common in medical image analysis. The main contribution of the paper is a mathematical formulation for incorporating soft model assignments into the calculation of affinities, which are traditionally model free. We integrate the resulting model-aware affinities into the multilevel segmentation by weighted aggregation algorithm. We apply the technique to the task of detecting and segmenting brain tumor and edema in multimodal MR volumes. Our results indicate the benefit of incorporating model-aware affinities into the segmentation process for the difficult case of brain tumor. |
| | |
Authors:
|
Jason J Corso; Eitan Sharon; Alan Yuille |
Related Documents
:
|
21737275 - Enhancing translation: guidelines for standard pre-clinical experiments in mdx mice. 19764955 - Segmentation and estimation for snp microarrays: a bayesian multiple change-point appro... 644185 - Non-invasive estimation of male bladder retention. 9288265 - Computed tomography data based rapid prototyping model of the temporal bone before coch... 19651425 - Modeling enterococcus densities measured by quantitative polymerase chain reaction and ... 18539275 - In vitro fertilization availability and utilization in the united states: a study of de... |
Publication Detail:
|
Type: Evaluation Studies; Journal Article; Research Support, N.I.H., Extramural |
Journal Detail:
|
Title: Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention Volume: 9 ISSN: - ISO Abbreviation: Med Image Comput Comput Assist Interv Publication Date: 2006 |
Date Detail:
|
Created Date: 2007-03-14 Completed Date: 2007-04-06 Revised Date: 2009-12-11 |
Medline Journal Info:
|
Nlm Unique ID: 101249582 Medline TA: Med Image Comput Comput Assist Interv Country: Germany |
Other Details:
|
Languages: eng Pagination: 790-8 Citation Subset: IM |
Affiliation:
|
Medical Imaging Informatics, University of California, Los Angeles, CA, USA. jcorso@mii.ucla.edu |
Export Citation:
|
APA/MLA Format Download EndNote Download BibTex |
| MeSH Terms | |
Descriptor/Qualifier:
|
Algorithms* Artificial Intelligence* Bayes Theorem Brain Neoplasms / pathology* Computer Simulation Humans Image Enhancement / methods* Image Interpretation, Computer-Assisted / methods* Imaging, Three-Dimensional / methods Magnetic Resonance Imaging / methods* Models, Biological Models, Statistical Pattern Recognition, Automated / methods* Reproducibility of Results Sensitivity and Specificity |
| Grant Support | |
ID/Acronym/Agency:
|
LM07356/LM/NLM NIH HHS |
From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine
Previous Document: Objective PET lesion segmentation using a spherical mean shift algorithm.
Next Document: A new adaptive probabilistic model of blood vessels for segmenting MRA images.