Document Detail


Methods for detecting functional classifications in neuroimaging data.
MedLine Citation:
PMID:  15340933     Owner:  NLM     Status:  MEDLINE    
Abstract/OtherAbstract:
Data-driven statistical methods are useful for examining the spatial organization of human brain function. Cluster analysis is one approach that aims to identify spatial classifications of temporal brain activity profiles. Numerous clustering algorithms are available, and no one method is optimal for all areas of application because an algorithm's performance depends on specific characteristics of the data. K-means and fuzzy clustering are popular for neuroimaging analyses, and select hierarchical procedures also appear in the literature. It is unclear which clustering methods perform best for neuroimaging data. We conduct a simulation study, based on PET neuroimaging data, to evaluate the performances of several clustering algorithms, including a new procedure that builds on the kth nearest neighbor method. We also examine three stopping rules that assist in determining the optimal number of clusters. Five hierarchical clustering algorithms perform best in our study, some of which are new to neuroimaging analyses, with Ward's and the beta-flexible methods exhibiting the strongest performances. Furthermore, Ward's and the beta-flexible methods yield the best performances for noisy data, and the popular K-means and fuzzy clustering procedures also perform reasonably well. The stopping rules also exhibit good performances for the top five clustering algorithms, and the pseudo-T2 and pseudo-F stopping rules are superior for noisy data. Based on our simulations for both noisy and unscaled PET neuroimaging data, we recommend the combined use of the pseudo-F or pseudo-T2 stopping rule along with either Ward's or the beta-flexible clustering algorithm.
Authors:
F DuBois Bowman; Rajan Patel; Chengxing Lu
Related Documents :
19579053 - Multivariate analysis for characteristics of heat tolerance in horses in brazil.
19766993 - An examination of nubian and egyptian biological distances: support for biological diff...
10414033 - A random walk model of oligodendrocyte generation in vitro and associated estimation pr...
Publication Detail:
Type:  Comparative Study; Journal Article; Research Support, U.S. Gov't, P.H.S.    
Journal Detail:
Title:  Human brain mapping     Volume:  23     ISSN:  1065-9471     ISO Abbreviation:  Hum Brain Mapp     Publication Date:  2004 Oct 
Date Detail:
Created Date:  2004-09-01     Completed Date:  2004-12-23     Revised Date:  2007-11-14    
Medline Journal Info:
Nlm Unique ID:  9419065     Medline TA:  Hum Brain Mapp     Country:  United States    
Other Details:
Languages:  eng     Pagination:  109-19     Citation Subset:  IM    
Affiliation:
Department of Biostatistics, Rollins School of Public Health, Emory University, Atlanta, Georgia 30322, USA. dbowma3@sph.emory.edu
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Algorithms*
Brain / physiology*,  radiography
Brain Mapping / methods*
Cluster Analysis*
Humans
Positron-Emission Tomography*
Reproducibility of Results
Grant Support
ID/Acronym/Agency:
K25-MH65473/MH/NIMH NIH HHS

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


Previous Document:  Brain-behavior correlation in children depends on the neurocognitive network.
Next Document:  Realistic spatial sampling for MEG beamformer images.