Document Detail


Classifier selection strategies for label fusion using large atlas databases.
MedLine Citation:
PMID:  18051099     Owner:  NLM     Status:  MEDLINE    
Abstract/OtherAbstract:
Structural segmentations of brain MRI can be generated by propagating manually labelled atlas images from a repository to a query subject and combining them. This method has been shown to be robust, consistent and increasingly accurate with increasing numbers of classifiers. It outperforms standard atlas-based segmentation but suffers, however, from problems of scale when the number of atlases is large. For a large repository and a particular query subject, using a selection strategy to identify good classifiers is one way to address problems of scale. This work presents and compares different classifier selection strategies which are applied to a group of 275 subjects with manually labelled brain MR images. We approximate an upper limit for the accuracy or overlap that can be achieved for a particular structure in a given subject and compare this with the accuracy obtained using classifier selection. The accuracy of different classifier selection strategies are also rated against the distribution of overlaps generated by random groups of classifiers.
Authors:
P Aljabar; R Heckemann; A Hammers; J V Hajnal; D Rueckert
Related Documents :
21799599 - Ileosigmoid knot: a case report.
19163469 - Pca-sga implementation in classification and disease specific feature extraction of the...
22304959 - Early detection of placental inflammation by mri enabling protection by clinically rele...
3506139 - Post-traumatic defects in computed tomography.
22826399 - Comparison of ct-based methodologies for detection of growth of solid renal masses on a...
9345539 - Applications of dynamic susceptibility contrast magnetic resonance imaging in neuropsyc...
22108749 - Magnetic resonance imaging of acute scrotum.
2025499 - New trends in computed tomography of the head and neck.
22842379 - Methotrexate-induced acute toxic leukoencephalopathy.
Publication Detail:
Type:  Journal Article; Research Support, Non-U.S. Gov't    
Journal Detail:
Title:  Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention     Volume:  10     ISSN:  -     ISO Abbreviation:  Med Image Comput Comput Assist Interv     Publication Date:  2007  
Date Detail:
Created Date:  2007-12-04     Completed Date:  2008-01-03     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:  523-31     Citation Subset:  IM    
Affiliation:
Department of Computing, Imperial College London, UK.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Algorithms
Artificial Intelligence*
Brain / anatomy & histology*
Databases, Factual*
Humans
Image Enhancement / methods
Image Interpretation, Computer-Assisted / methods*
Imaging, Three-Dimensional / methods
Information Storage and Retrieval / methods
Magnetic Resonance Imaging / methods*
Pattern Recognition, Automated / methods*
Reproducibility of Results
Sensitivity and Specificity
Subtraction Technique*

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


Previous Document:  Automatic inference of sulcus patterns using 3D moment invariants.
Next Document:  Groupwise combined segmentation and registration for atlas construction.