Paper Info
Title
Classification and Visualization of Multiclass fMRI Data Using Supervised Self-Organizing Maps.
Abstract
So far, most fMRI studies that analyzed voxel activity patterns of more than two conditions transformed the multiclass problem into a series of binary problems. Furthermore, visualizations of the topology of underlying representations are usually not presented. Here, we explore the feasibility of different types of supervised self-organizing maps (SSOM) to decode and visualize voxel patterns of fMRI datasets consisting of multiple conditions. Our results suggest that - compared to commonly applied classification approaches - SSOMs are well suited when activity patterns consist of a small number of features (e.g. as in searchlight- or region of interest- based approaches). In addition, we demonstrate the utility of using SOM grids for intuitive and exploratory visualization of topological relations among classes of fMRI activity patterns.
Year
DOI
Venue
2012
10.1109/PRNI.2012.34
PRNI
Keywords
Field
DocType
fmri activity pattern,som grid,voxel pattern,binary problem,supervised self-organizing maps,fmri datasets,different type,fmri study,voxel activity pattern,classification approach,activity pattern,multiclass fmri data,support vector machines,topology,multiclass classification,image classification,classification algorithms,decoding,data visualisation,signal to noise ratio,stability analysis,vectors,self organizing maps
Voxel,Data visualization,Pattern recognition,Visualization,Computer science,Self-organizing map,Artificial intelligence,Region of interest,Decoding methods,Contextual image classification,Machine learning,Multiclass classification
Conference
Citations 
PageRank 
References 
1
0.35
4
Authors
4
Name
Order
Citations
PageRank
Lars Haufeld110.35
Roberta Santoro210.35
Giancarlo Valente312710.62
Elia Formisano477858.91