Home > Publications database > Deep neural networks and kernel regression achieve comparable accuracies for functional connectivity prediction of behavior and demographics > print

001     865865
005     20210130003204.0
024 7 _ |a 10.1016/j.neuroimage.2019.116276
|2 doi
024 7 _ |a 1053-8119
|2 ISSN
024 7 _ |a 1095-9572
|2 ISSN
024 7 _ |a 2128/23997
|2 Handle
024 7 _ |a altmetric:68252714
|2 altmetric
024 7 _ |a pmid:31610298
|2 pmid
024 7 _ |a WOS:000507987000012
|2 WOS
037 _ _ |a FZJ-2019-05152
082 _ _ |a 610
100 1 _ |a He, Tong
|0 P:(DE-HGF)0
|b 0
245 _ _ |a Deep neural networks and kernel regression achieve comparable accuracies for functional connectivity prediction of behavior and demographics
260 _ _ |a Orlando, Fla.
|c 2020
|b Academic Press
336 7 _ |a article
|2 DRIVER
336 7 _ |a Output Types/Journal article
|2 DataCite
336 7 _ |a Journal Article
|b journal
|m journal
|0 PUB:(DE-HGF)16
|s 1579705295_19654
|2 PUB:(DE-HGF)
336 7 _ |a ARTICLE
|2 BibTeX
336 7 _ |a JOURNAL_ARTICLE
|2 ORCID
336 7 _ |a Journal Article
|0 0
|2 EndNote
520 _ _ |a There is significant interest in the development and application of deep neural networks (DNNs) to neuroimaging data. A growing literature suggests that DNNs outperform their classical counterparts in a variety of neuroimaging applications, yet there are few direct comparisons of relative utility. Here, we compared the performance of three DNN architectures and a classical machine learning algorithm (kernel regression) in predicting individual phenotypes from whole-brain resting-state functional connectivity (RSFC) patterns. One of the DNNs was a generic fully-connected feedforward neural network, while the other two DNNs were recently published approaches specifically designed to exploit the structure of connectome data. By using a combined sample of almost 10,000 participants from the Human Connectome Project (HCP) and UK Biobank, we showed that the three DNNs and kernel regression achieved similar performance across a wide range of behavioral and demographic measures. Furthermore, the generic feedforward neural network exhibited similar performance to the two state-of-the-art connectome-specific DNNs. When predicting fluid intelligence in the UK Biobank, performance of all algorithms dramatically improved when sample size increased from 100 to 1000 subjects. Improvement was smaller, but still significant, when sample size increased from 1000 to 5000 subjects. Importantly, kernel regression was competitive across all sample sizes. Overall, our study suggests that kernel regression is as effective as DNNs for RSFC-based behavioral prediction, while incurring significantly lower computational costs. Therefore, kernel regression might serve as a useful baseline algorithm for future studies.
536 _ _ |a 571 - Connectivity and Activity (POF3-571)
|0 G:(DE-HGF)POF3-571
|c POF3-571
|f POF III
|x 0
588 _ _ |a Dataset connected to CrossRef
700 1 _ |a Kong, Ru
|0 P:(DE-HGF)0
|b 1
700 1 _ |a Holmes, Avram J.
|0 P:(DE-HGF)0
|b 2
700 1 _ |a Nguyen, Minh
|0 P:(DE-HGF)0
|b 3
700 1 _ |a Sabuncu, Mert R.
|0 P:(DE-HGF)0
|b 4
700 1 _ |a Eickhoff, Simon B.
|0 P:(DE-Juel1)131678
|b 5
700 1 _ |a Bzdok, Danilo
|0 P:(DE-Juel1)136848
|b 6
700 1 _ |a Feng, Jiashi
|0 P:(DE-HGF)0
|b 7
700 1 _ |a Thomas Yeo, B. T.
|0 P:(DE-HGF)0
|b 8
|e Corresponding author
773 _ _ |a 10.1016/j.neuroimage.2019.116276
|g p. 116276 -
|0 PERI:(DE-600)1471418-8
|p 116276
|t NeuroImage
|v 206
|y 2020
|x 1053-8119
856 4 _ |y OpenAccess
|u https://juser.fz-juelich.de/record/865865/files/1-s2.0-S1053811919308675-main.pdf
856 4 _ |y OpenAccess
|x pdfa
|u https://juser.fz-juelich.de/record/865865/files/1-s2.0-S1053811919308675-main.pdf?subformat=pdfa
909 C O |o oai:juser.fz-juelich.de:865865
|p openaire
|p open_access
|p VDB
|p driver
|p dnbdelivery
910 1 _ |a Forschungszentrum Jülich
|0 I:(DE-588b)5008462-8
|k FZJ
|b 5
|6 P:(DE-Juel1)131678
913 1 _ |a DE-HGF
|b Key Technologies
|l Decoding the Human Brain
|1 G:(DE-HGF)POF3-570
|0 G:(DE-HGF)POF3-571
|2 G:(DE-HGF)POF3-500
|v Connectivity and Activity
|x 0
|4 G:(DE-HGF)POF
|3 G:(DE-HGF)POF3
914 1 _ |y 2020
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0200
|2 StatID
|b SCOPUS
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)1030
|2 StatID
|b Current Contents - Life Sciences
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0600
|2 StatID
|b Ebsco Academic Search
915 _ _ |a Creative Commons Attribution-NonCommercial-NoDerivs CC BY-NC-ND 4.0
|0 LIC:(DE-HGF)CCBYNCND4
|2 HGFVOC
915 _ _ |a JCR
|0 StatID:(DE-HGF)0100
|2 StatID
|b NEUROIMAGE : 2017
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0150
|2 StatID
|b Web of Science Core Collection
915 _ _ |a WoS
|0 StatID:(DE-HGF)0110
|2 StatID
|b Science Citation Index
915 _ _ |a WoS
|0 StatID:(DE-HGF)0111
|2 StatID
|b Science Citation Index Expanded
915 _ _ |a OpenAccess
|0 StatID:(DE-HGF)0510
|2 StatID
915 _ _ |a Peer Review
|0 StatID:(DE-HGF)0030
|2 StatID
|b ASC
915 _ _ |a IF >= 5
|0 StatID:(DE-HGF)9905
|2 StatID
|b NEUROIMAGE : 2017
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0310
|2 StatID
|b NCBI Molecular Biology Database
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)1050
|2 StatID
|b BIOSIS Previews
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0300
|2 StatID
|b Medline
915 _ _ |a Nationallizenz
|0 StatID:(DE-HGF)0420
|2 StatID
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0199
|2 StatID
|b Clarivate Analytics Master Journal List
920 _ _ |l yes
920 1 _ |0 I:(DE-Juel1)INM-7-20090406
|k INM-7
|l Gehirn & Verhalten
|x 0
980 _ _ |a journal
980 _ _ |a VDB
980 _ _ |a UNRESTRICTED
980 _ _ |a I:(DE-Juel1)INM-7-20090406
980 1 _ |a FullTexts

LibraryCollectionCLSMajorCLSMinorLanguageAuthor
Marc 21