schliessen

Filtern

 

Bibliotheken

Combining multivariate voxel selection and support vector machines for mapping and classification of fMRI spatial patterns

In functional brain mapping, pattern recognition methods allow detecting multivoxel patterns of brain activation which are informative with respect to a subject's perceptual or cognitive state. The sensitivity of these methods, however, is greatly reduced when the proportion of voxels that convey th... Full description

Journal Title: Neuroimage 2008, Vol.43(1), pp.44-58
Main Author: De Martino, Federico
Other Authors: Valente, Giancarlo , Staeren, Noël , Ashburner, John , Goebel, Rainer , Formisano, Elia
Format: Electronic Article Electronic Article
Language: English
Subjects:
ID: ISSN: 1053-8119 ; E-ISSN: 1095-9572 ; DOI: 10.1016/j.neuroimage.2008.06.037
Link: http://dx.doi.org/10.1016/j.neuroimage.2008.06.037
Zum Text:
SendSend as email Add to Book BagAdd to Book Bag
Staff View
recordid: elsevier_sdoi_10_1016_j_neuroimage_2008_06_037
title: Combining multivariate voxel selection and support vector machines for mapping and classification of fMRI spatial patterns
format: Article
creator:
  • De Martino, Federico
  • Valente, Giancarlo
  • Staeren, Noël
  • Ashburner, John
  • Goebel, Rainer
  • Formisano, Elia
subjects:
  • Medicine
ispartof: Neuroimage, 2008, Vol.43(1), pp.44-58
description: In functional brain mapping, pattern recognition methods allow detecting multivoxel patterns of brain activation which are informative with respect to a subject's perceptual or cognitive state. The sensitivity of these methods, however, is greatly reduced when the proportion of voxels that convey the discriminative information is small compared to the total number of measured voxels. To reduce this dimensionality problem, previous studies employed univariate voxel selection or region-of-interest-based strategies as a preceding step to the application of machine learning algorithms. Here we employ a strategy for classifying functional imaging data based on a multivariate feature selection algorithm, Recursive Feature Elimination (RFE) that uses the training algorithm (support vector machine) recursively to eliminate irrelevant voxels and estimate informative spatial patterns. Generalization performances on test data increases while features/voxels are pruned...
language: eng
source:
identifier: ISSN: 1053-8119 ; E-ISSN: 1095-9572 ; DOI: 10.1016/j.neuroimage.2008.06.037
fulltext: fulltext
issn:
  • 1053-8119
  • 10538119
  • 1095-9572
  • 10959572
url: Link


@attributes
ID1575411135
RANK0.07
NO1
SEARCH_ENGINEprimo_central_multiple_fe
SEARCH_ENGINE_TYPEPrimo Central Search Engine
LOCALfalse
PrimoNMBib
record
control
sourcerecordiddoi_10_1016_j_neuroimage_2008_06_037
sourceidelsevier_s
recordidTN_elsevier_sdoi_10_1016_j_neuroimage_2008_06_037
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
29AGHFR
30AGUBO
31AGWIK
32AGYEJ
33AHHHB
34AIKHN
35AITUG
36AJBFU
37AJOXV
38AJRQY
39AKRLJ
40AMFUW
41ANZVX
42BLXMC
43BNPGV
44EO8
45EO9
46EP2
47EP3
48FDB
49FGOYB
50FIRID
51FNPLU
52G-Q
53GBLVA
54HDW
55HEI
56HMK
57HMO
58HMQ
59J1W
60KOM
61LCYCR
62MOBAO
63OAUVE
64P-8
65P-9
66PC.
67Q38
68R2-
69RPZ
70SAE
71SCC
72SDF
73SDG
74SDP
75SES
76SEW
77SNS
78SSH
79SSN
80SSZ
81T5K
82UV1
83~G-
pqid1506754064
galeid186010447
display
typearticle
titleCombining multivariate voxel selection and support vector machines for mapping and classification of fMRI spatial patterns
creatorDe Martino, Federico ; Valente, Giancarlo ; Staeren, Noël ; Ashburner, John ; Goebel, Rainer ; Formisano, Elia
ispartofNeuroimage, 2008, Vol.43(1), pp.44-58
identifier
subjectMedicine
descriptionIn functional brain mapping, pattern recognition methods allow detecting multivoxel patterns of brain activation which are informative with respect to a subject's perceptual or cognitive state. The sensitivity of these methods, however, is greatly reduced when the proportion of voxels that convey the discriminative information is small compared to the total number of measured voxels. To reduce this dimensionality problem, previous studies employed univariate voxel selection or region-of-interest-based strategies as a preceding step to the application of machine learning algorithms. Here we employ a strategy for classifying functional imaging data based on a multivariate feature selection algorithm, Recursive Feature Elimination (RFE) that uses the training algorithm (support vector machine) recursively to eliminate irrelevant voxels and estimate informative spatial patterns. Generalization performances on test data increases while features/voxels are pruned...
languageeng
source
version8
lds50peer_reviewed
links
openurl$$Topenurl_article
openurlfulltext$$Topenurlfull_article
backlink$$Uhttp://dx.doi.org/10.1016/j.neuroimage.2008.06.037$$EView_record_in_ScienceDirect_(Access_to_full_text_may_be_restricted)
search
creatorcontrib
0De Martino, Federico
1Valente, Giancarlo
2Staeren, Noël
3Ashburner, John
4Goebel, Rainer
5Formisano, Elia
titleCombining multivariate voxel selection and support vector machines for mapping and classification of fMRI spatial patterns
description

In functional brain mapping, pattern recognition methods allow detecting multivoxel patterns of brain activation which are informative with respect to a subject's perceptual or cognitive state. The sensitivity of these methods, however, is greatly reduced when the proportion of voxels that convey the discriminative information is small compared to the total number of measured voxels. To reduce this dimensionality problem, previous studies employed univariate voxel selection or region-of-interest-based strategies as a preceding step to the application of machine learning algorithms.

Here we employ a strategy for classifying functional imaging data based on a multivariate feature selection algorithm, Recursive Feature Elimination (RFE) that uses the training algorithm (support vector machine) recursively to eliminate irrelevant voxels and estimate informative spatial patterns. Generalization performances on test data increases while features/voxels are pruned...

subjectMedicine
general
0English
1Elsevier Inc
210.1016/j.neuroimage.2008.06.037
3ScienceDirect (Elsevier)
4ScienceDirect Journals (Elsevier)
sourceidelsevier_s
recordidelsevier_sdoi_10_1016_j_neuroimage_2008_06_037
issn
01053-8119
110538119
21095-9572
310959572
rsrctypearticle
creationdate2008
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
29AGHFR
30AGUBO
31AGWIK
32AGYEJ
33AHHHB
34AIKHN
35AITUG
36AJBFU
37AJOXV
38AJRQY
39AKRLJ
40AMFUW
41ANZVX
42BLXMC
43BNPGV
44EO8
45EO9
46EP2
47EP3
48FDB
49FGOYB
50FIRID
51FNPLU
52G-Q
53GBLVA
54HDW
55HEI
56HMK
57HMO
58HMQ
59J1W
60KOM
61LCYCR
62MOBAO
63OAUVE
64P-8
65P-9
66PC.
67Q38
68R2-
69RPZ
70SAE
71SCC
72SDF
73SDG
74SDP
75SES
76SEW
77SNS
78SSH
79SSN
80SSZ
81T5K
82UV1
83~G-
startdate20080101
enddate20081231
lsr40Neuroimage, 2008, Vol.43 (1), pp.44-58
doi10.1016/j.neuroimage.2008.06.037
citationpf 44 pt 58 vol 43 issue 1
lsr30VSR-Enriched:[pqid, galeid]
sort
titleCombining multivariate voxel selection and support vector machines for mapping and classification of fMRI spatial patterns
authorDe Martino, Federico ; Valente, Giancarlo ; Staeren, Noël ; Ashburner, John ; Goebel, Rainer ; Formisano, Elia
creationdate20080000
lso0120080000
facets
frbrgroupid3225680746286646183
frbrtype5
newrecords20190904
languageeng
topicMedicine
collectionScienceDirect (Elsevier)
prefilterarticles
rsrctypearticles
creatorcontrib
0De Martino, Federico
1Valente, Giancarlo
2Staeren, Noël
3Ashburner, John
4Goebel, Rainer
5Formisano, Elia
jtitleNeuroimage
creationdate2008
toplevelpeer_reviewed
delivery
delcategoryRemote Search Resource
fulltextfulltext
addata
aulast
0De Martino
1Valente
2Staeren
3Ashburner
4Goebel
5Formisano
aufirst
0Federico
1Giancarlo
2Noël
3John
4Rainer
5Elia
auinitF
auinit1F
au
0De Martino, Federico
1Valente, Giancarlo
2Staeren, Noël
3Ashburner, John
4Goebel, Rainer
5Formisano, Elia
atitleCombining multivariate voxel selection and support vector machines for mapping and classification of fMRI spatial patterns
jtitleNeuroimage
date2008
risdate2008
volume43
issue1
spage44
epage58
pages44-58
issn1053-8119
eissn1095-9572
formatjournal
genrearticle
ristypeJOUR
abstract

In functional brain mapping, pattern recognition methods allow detecting multivoxel patterns of brain activation which are informative with respect to a subject's perceptual or cognitive state. The sensitivity of these methods, however, is greatly reduced when the proportion of voxels that convey the discriminative information is small compared to the total number of measured voxels. To reduce this dimensionality problem, previous studies employed univariate voxel selection or region-of-interest-based strategies as a preceding step to the application of machine learning algorithms.

Here we employ a strategy for classifying functional imaging data based on a multivariate feature selection algorithm, Recursive Feature Elimination (RFE) that uses the training algorithm (support vector machine) recursively to eliminate irrelevant voxels and estimate informative spatial patterns. Generalization performances on test data increases while features/voxels are pruned...

pubElsevier Inc
doi10.1016/j.neuroimage.2008.06.037
lad01Neuroimage