schliessen

Filtern

 

Bibliotheken

Multiclass fMRI data decoding and visualization using supervised self-organizing maps

When multivariate pattern decoding is applied to fMRI studies entailing more than two experimental conditions, a most common approach is to transform the multiclass classification problem into a series of binary problems. Furthermore, for decoding analyses, classification accuracy is often the only... Full description

Journal Title: NeuroImage 01 August 2014, Vol.96, pp.54-66
Main Author: Hausfeld, Lars
Other Authors: Valente, Giancarlo , Formisano, Elia
Format: Electronic Article Electronic Article
Language: English
Subjects:
ID: ISSN: 1053-8119 ; E-ISSN: 1095-9572 ; DOI: 10.1016/j.neuroimage.2014.02.006
Link: http://dx.doi.org/10.1016/j.neuroimage.2014.02.006
Zum Text:
SendSend as email Add to Book BagAdd to Book Bag
Staff View
recordid: elsevier_sdoi_10_1016_j_neuroimage_2014_02_006
title: Multiclass fMRI data decoding and visualization using supervised self-organizing maps
format: Article
creator:
  • Hausfeld, Lars
  • Valente, Giancarlo
  • Formisano, Elia
subjects:
  • Fmri
  • Decoding
  • Multiclass Classification
  • Self-Organizing Maps
  • Fmri
  • Decoding
  • Multiclass Classification
  • Self-Organizing Maps
  • Medicine
ispartof: NeuroImage, 01 August 2014, Vol.96, pp.54-66
description: When multivariate pattern decoding is applied to fMRI studies entailing more than two experimental conditions, a most common approach is to transform the multiclass classification problem into a series of binary problems. Furthermore, for decoding analyses, classification accuracy is often the only outcome reported although the topology of activation patterns in the high-dimensional features space may provide additional insights into underlying brain representations. Here we propose to decode and visualize voxel patterns of fMRI datasets consisting of multiple conditions with a supervised variant of self-organizing maps (SSOMs). Using simulations and real fMRI data, we evaluated the performance of our SSOM-based approach. Specifically, the analysis of simulated fMRI data with varying signal-to-noise and contrast-to-noise ratio suggested that SSOMs perform better than a k-nearest-neighbor classifier for medium and large numbers of features (i.e. 250 to 1000 or more voxels) and...
language: eng
source:
identifier: ISSN: 1053-8119 ; E-ISSN: 1095-9572 ; DOI: 10.1016/j.neuroimage.2014.02.006
fulltext: fulltext
issn:
  • 1053-8119
  • 10538119
  • 1095-9572
  • 10959572
url: Link


@attributes
ID1334168787
RANK0.07
NO1
SEARCH_ENGINEprimo_central_multiple_fe
SEARCH_ENGINE_TYPEPrimo Central Search Engine
LOCALfalse
PrimoNMBib
record
control
sourcerecordiddoi_10_1016_j_neuroimage_2014_02_006
sourceidelsevier_s
recordidTN_elsevier_sdoi_10_1016_j_neuroimage_2014_02_006
sourcesystemPC
dbid
0--K
1--M
2.~1
31B1
41RT
51~.
6457
74G.
86I.
97-5
108P~
119JM
12AABNK
13AAEDT
14AAKOC
15AAOAW
16AAQFI
17AAXLA
18ABBQC
19ABCQJ
20ABFNM
21ABMZM
22ABYKQ
23ACDAQ
24ACRLP
25AEKER
26AFKWA
27AFTJW
28AFXIZ
29AGUBO
30AGWIK
31AGYEJ
32AIKHN
33AITUG
34AJBFU
35AJOXV
36AJRQY
37AMFUW
38ANZVX
39BLXMC
40BNPGV
41EO8
42EO9
43EP2
44EP3
45FDB
46FIRID
47FNPLU
48G-Q
49GBLVA
50J1W
51KOM
52LCYCR
53MOBAO
54OAUVE
55P-8
56P-9
57PC.
58Q38
59RPZ
60SCC
61SDF
62SDG
63SDP
64SES
65SSH
66SSN
67SSZ
68T5K
69UV1
70~G-
pqid1532479457
display
typearticle
titleMulticlass fMRI data decoding and visualization using supervised self-organizing maps
creatorHausfeld, Lars ; Valente, Giancarlo ; Formisano, Elia
ispartofNeuroImage, 01 August 2014, Vol.96, pp.54-66
identifier
subjectFmri ; Decoding ; Multiclass Classification ; Self-Organizing Maps ; Fmri ; Decoding ; Multiclass Classification ; Self-Organizing Maps ; Medicine
descriptionWhen multivariate pattern decoding is applied to fMRI studies entailing more than two experimental conditions, a most common approach is to transform the multiclass classification problem into a series of binary problems. Furthermore, for decoding analyses, classification accuracy is often the only outcome reported although the topology of activation patterns in the high-dimensional features space may provide additional insights into underlying brain representations. Here we propose to decode and visualize voxel patterns of fMRI datasets consisting of multiple conditions with a supervised variant of self-organizing maps (SSOMs). Using simulations and real fMRI data, we evaluated the performance of our SSOM-based approach. Specifically, the analysis of simulated fMRI data with varying signal-to-noise and contrast-to-noise ratio suggested that SSOMs perform better than a k-nearest-neighbor classifier for medium and large numbers of features (i.e. 250 to 1000 or more voxels) and...
languageeng
source
version6
lds50peer_reviewed
links
openurl$$Topenurl_article
openurlfulltext$$Topenurlfull_article
backlink$$Uhttp://dx.doi.org/10.1016/j.neuroimage.2014.02.006$$EView_record_in_ScienceDirect_(Access_to_full_text_may_be_restricted)
search
creatorcontrib
0Hausfeld, Lars
1Valente, Giancarlo
2Formisano, Elia
titleMulticlass fMRI data decoding and visualization using supervised self-organizing maps
description

When multivariate pattern decoding is applied to fMRI studies entailing more than two experimental conditions, a most common approach is to transform the multiclass classification problem into a series of binary problems. Furthermore, for decoding analyses, classification accuracy is often the only outcome reported although the topology of activation patterns in the high-dimensional features space may provide additional insights into underlying brain representations. Here we propose to decode and visualize voxel patterns of fMRI datasets consisting of multiple conditions with a supervised variant of self-organizing maps (SSOMs). Using simulations and real fMRI data, we evaluated the performance of our SSOM-based approach. Specifically, the analysis of simulated fMRI data with varying signal-to-noise and contrast-to-noise ratio suggested that SSOMs perform better than a k-nearest-neighbor classifier for medium and large numbers of features (i.e. 250 to 1000 or more voxels) and...

subject
0Fmri
1Decoding
2Multiclass Classification
3Self-Organizing Maps
4Medicine
general
0English
1Elsevier Inc
210.1016/j.neuroimage.2014.02.006
3ScienceDirect (Elsevier)
4ScienceDirect Journals (Elsevier)
sourceidelsevier_s
recordidelsevier_sdoi_10_1016_j_neuroimage_2014_02_006
issn
01053-8119
110538119
21095-9572
310959572
rsrctypearticle
creationdate2014
addtitleNeuroImage
searchscope
0elsevier_full
1elsevier2
scope
0elsevier_full
1elsevier2
lsr44$$EView_record_in_ScienceDirect_(Access_to_full_text_may_be_restricted)
tmp01ScienceDirect Journals (Elsevier)
tmp02
0--K
1--M
2.~1
31B1
41RT
51~.
6457
74G.
86I.
97-5
108P~
119JM
12AABNK
13AAEDT
14AAKOC
15AAOAW
16AAQFI
17AAXLA
18ABBQC
19ABCQJ
20ABFNM
21ABMZM
22ABYKQ
23ACDAQ
24ACRLP
25AEKER
26AFKWA
27AFTJW
28AFXIZ
29AGUBO
30AGWIK
31AGYEJ
32AIKHN
33AITUG
34AJBFU
35AJOXV
36AJRQY
37AMFUW
38ANZVX
39BLXMC
40BNPGV
41EO8
42EO9
43EP2
44EP3
45FDB
46FIRID
47FNPLU
48G-Q
49GBLVA
50J1W
51KOM
52LCYCR
53MOBAO
54OAUVE
55P-8
56P-9
57PC.
58Q38
59RPZ
60SCC
61SDF
62SDG
63SDP
64SES
65SSH
66SSN
67SSZ
68T5K
69UV1
70~G-
startdate20140801
enddate20140801
lsr40NeuroImage, 01 August 2014, Vol.96, pp.54-66
doi10.1016/j.neuroimage.2014.02.006
citationpf 54 pt 66 vol 96
lsr30VSR-Enriched:[pqid]
sort
titleMulticlass fMRI data decoding and visualization using supervised self-organizing maps
authorHausfeld, Lars ; Valente, Giancarlo ; Formisano, Elia
creationdate20140801
lso0120140801
facets
frbrgroupid446571001121447777
frbrtype5
newrecords20190904
languageeng
topic
0Fmri
1Decoding
2Multiclass Classification
3Self-Organizing Maps
4Medicine
collectionScienceDirect (Elsevier)
prefilterarticles
rsrctypearticles
creatorcontrib
0Hausfeld, Lars
1Valente, Giancarlo
2Formisano, Elia
jtitleNeuroImage
creationdate2014
toplevelpeer_reviewed
delivery
delcategoryRemote Search Resource
fulltextfulltext
addata
aulast
0Hausfeld
1Valente
2Formisano
aufirst
0Lars
1Giancarlo
2Elia
auinitL
auinit1L
au
0Hausfeld, Lars
1Valente, Giancarlo
2Formisano, Elia
atitleMulticlass fMRI data decoding and visualization using supervised self-organizing maps
jtitleNeuroImage
risdate20140801
volume96
spage54
epage66
pages54-66
issn1053-8119
eissn1095-9572
formatjournal
genrearticle
ristypeJOUR
abstract

When multivariate pattern decoding is applied to fMRI studies entailing more than two experimental conditions, a most common approach is to transform the multiclass classification problem into a series of binary problems. Furthermore, for decoding analyses, classification accuracy is often the only outcome reported although the topology of activation patterns in the high-dimensional features space may provide additional insights into underlying brain representations. Here we propose to decode and visualize voxel patterns of fMRI datasets consisting of multiple conditions with a supervised variant of self-organizing maps (SSOMs). Using simulations and real fMRI data, we evaluated the performance of our SSOM-based approach. Specifically, the analysis of simulated fMRI data with varying signal-to-noise and contrast-to-noise ratio suggested that SSOMs perform better than a k-nearest-neighbor classifier for medium and large numbers of features (i.e. 250 to 1000 or more voxels) and...

pubElsevier Inc
doi10.1016/j.neuroimage.2014.02.006
lad01NeuroImage
date2014-08-01