Document Detail


Comparison of four shape features for detecting hippocampal shape changes in early Alzheimer's.
MedLine Citation:
PMID:  22653846     Owner:  NLM     Status:  Publisher    
Abstract/OtherAbstract:
We compare four methods for generating shape-based features from 3D binary images of the hippocampus for use in group discrimination and classification. The first method we investigate is based on decomposing the hippocampal binary segmentation onto an orthonormal basis of spherical harmonics, followed by computation of shape invariants by tensor contraction using the Clebsch-Gordan coefficients. The second method we investigate is based on the classical 3D moment invariants; these are a special case of the spherical harmonics-based tensor invariants. The third method is based on solving the Helmholtz equation on the geometry of the binary hippocampal segmentation, and construction of shape-descriptive features from the eigenvalues of the Fourier-like modes of the geometry represented by the Laplacian eigenfunctions. The fourth method investigates the use of initial momentum obtained from the large-deformation diffeomorphic metric mapping method as a shape feature. Each of these shape features is tested for group differences in the control (Clinical Dementia Rating Scale CDR 0) and the early (very mild) Alzheimer's (CDR 0.5) population. Classification of individual shapes is performed via a linear support vector machine based classifer with leave-one-out cross validation to test for overall performance. These experiments show that all of these feature computation approaches gave stable and reasonable classification results on the same database, and with the same classifier. The best performance was achieved with the shape-features constructed from large-deformation diffeomorphic metric mapping-based initial momentum.
Authors:
Mirza Faisal Beg; Pradeep Reddy Raamana; Sebastiano Barbieri; Lei Wang
Related Documents :
24080706 - Gaussian process-mixture conditional heteroscedasticity.
24418626 - Chimpocentrism and reconstructions of human evolution (a timely reminder).
24301536 - An enhanced developmental staging table for the painted turtle, chrysemys picta (testud...
24622336 - Caspian: a causal compressive sensing algorithm for discovering directed interactions i...
21359806 - Propagation, storage, and assays with hyaloperonospora arabidopsidis: a model oomycete ...
1597746 - A region of interest strategy for minimizing resolution distortions in quantitative myo...
Publication Detail:
Type:  JOURNAL ARTICLE     Date:  2012-5-30
Journal Detail:
Title:  Statistical methods in medical research     Volume:  -     ISSN:  1477-0334     ISO Abbreviation:  -     Publication Date:  2012 May 
Date Detail:
Created Date:  2012-6-1     Completed Date:  -     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  9212457     Medline TA:  Stat Methods Med Res     Country:  -    
Other Details:
Languages:  ENG     Pagination:  -     Citation Subset:  -    
Affiliation:
Medical Image Analysis Laboratory, School of Engineering Science, Simon Fraser University, Burnaby, BC, Canada.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:

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


Previous Document:  Activation of Wnt Signalling promotes development of dysplasia in Barrett's Oesophagus.
Next Document:  On the P-Coordinating Limit of NHC-Phosphenium Cations toward Rh(I) Centers.