Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
A Similarity Retrieval Method for Functional Magnetic Resonance Imaging (fMRI) Statistical Maps
 

Summary: A Similarity Retrieval Method for Functional Magnetic
Resonance Imaging (fMRI) Statistical Maps
R. F. Tungarazaa, J. Guana, S. Rolfec, I. Atmosukartoa, A. Poliakovd,
N. M. Kleinhanse, E. Aylwarde, J. Ojemannb, J. F. Brinkleyd, and L. G. Shapiro a
aComputer Science and Engineering, Box 352350, U. of Washington, Seattle, WA, USA 98195;
bNeurological Surgery, Children's Hospital, 4800 Sand Point Way, Seattle, WA, USA 98105;
cElectrical Engineering, Box 352500, U. of Washington, Seattle, WA, USA 98195;
dBiological Structure, Box 357420, U. of Washington, Seattle, WA, USA 98195;
eRadiology, Box 375115, U. of Washington, Seattle, WA, USA 98195
ABSTRACT
We propose a method for retrieving similar fMRI statistical images given a query fMRI image and a database
of such images. Our method creates a feature vector for each spatially distinct region within each such image in
the database. The similarity between two images is obtained by the summed minimum distance (SMD) of their
constituent feature vectors. Results on a dataset of fMRI statistical images from experiments involving three
distinct cognitive tasks suggest that this method is able to capture the differences in activation patterns due to
differences in the cognitive tasks performed.
Keywords: Functional imaging, Pattern recognition
1. DESCRIPTION OF PURPOSE
Statistical analysis on fMRI data culminate with the generation of statistical maps (e.g. Z-scores, T-scores, or
F-scores) for individual subjects and/or groups of subjects. Consider a scenario where a number of research

  

Source: Anderson, Richard - Department of Computer Science and Engineering, University of Washington at Seattle

 

Collections: Computer Technologies and Information Sciences