000891374 001__ 891374
000891374 005__ 20230815122843.0
000891374 020__ $$a978-3-030-67669-8 (print)
000891374 020__ $$a978-3-030-67670-4 (electronic)
000891374 0247_ $$2doi$$a10.1007/978-3-030-67670-4_1
000891374 0247_ $$2ISSN$$a0302-9743
000891374 0247_ $$2ISSN$$a1611-3349
000891374 0247_ $$2Handle$$a2128/27537
000891374 0247_ $$2WOS$$aWOS:000716884800001
000891374 037__ $$aFZJ-2021-01463
000891374 1001_ $$0P:(DE-HGF)0$$aDong, Yuxiao$$b0$$eEditor
000891374 245__ $$aConfound Removal and Normalization in Practice: A Neuroimaging Based Sex Prediction Case Study
000891374 260__ $$aCham$$bSpringer International Publishing$$c2021
000891374 29510 $$aMachine Learning and Knowledge Discovery in Databases. Applied Data Science and Demo Track / Dong, Yuxiao (Editor) ; Cham : Springer International Publishing, 2021, Chapter 1 ; ISSN: 0302-9743=1611-3349 ; ISBN: 978-3-030-67669-8=978-3-030-67670-4 ; doi:10.1007/978-3-030-67670-4
000891374 300__ $$a3 - 18
000891374 3367_ $$2ORCID$$aBOOK_CHAPTER
000891374 3367_ $$07$$2EndNote$$aBook Section
000891374 3367_ $$2DRIVER$$abookPart
000891374 3367_ $$2BibTeX$$aINBOOK
000891374 3367_ $$2DataCite$$aOutput Types/Book chapter
000891374 3367_ $$0PUB:(DE-HGF)7$$2PUB:(DE-HGF)$$aContribution to a book$$bcontb$$mcontb$$s1617966925_9159
000891374 4900_ $$aLecture Notes in Computer Science$$v12461
000891374 520__ $$aMachine learning (ML) methods are increasingly being used to predict pathologies and biological traits using neuroimaging data. Here controlling for confounds is essential to get unbiased estimates of generalization performance and to identify the features driving predictions. However, a systematic evaluation of the advantages and disadvantages of available alternatives is lacking. This makes it difficult to compare results across studies and to build deployment quality models. Here, we evaluated two commonly used confound removal schemes–whole data confound regression (WDCR) and cross-validated confound regression (CVCR)–to understand their effectiveness and biases induced in generalization performance estimation. Additionally, we study the interaction of the confound removal schemes with Z-score normalization, a common practice in ML modelling. We applied eight combinations of confound removal schemes and normalization (pipelines) to decode sex from resting-state functional MRI (rfMRI) data while controlling for two confounds, brain size and age. We show that both schemes effectively remove linear univariate and multivariate confounding effects resulting in reduced model performance with CVCR providing better generalization estimates, i.e., closer to out-of-sample performance than WDCR. We found no effect of normalizing before or after confound removal. In the presence of dataset and confound shift, four tested confound removal procedures yielded mixed results, raising new questions. We conclude that CVCR is a better method to control for confounding effects in neuroimaging studies. We believe that our in-depth analyses shed light on choices associated with confound removal and hope that it generates more interest in this problem instrumental to numerous applications.
000891374 536__ $$0G:(DE-HGF)POF4-525$$a525 - Decoding Brain Organization and Dysfunction (POF4-525)$$cPOF4-525$$fPOF IV$$x0
000891374 536__ $$0G:(GEPRIS)432015680$$aDFG project 432015680 - Automatisierte Gehirnalterung-Vorhersage und deren Interpretation $$c432015680$$x1
000891374 588__ $$aDataset connected to CrossRef Book Series
000891374 7001_ $$0P:(DE-HGF)0$$aIfrim, Georgiana$$b1$$eEditor
000891374 7001_ $$0P:(DE-HGF)0$$aMladenić, Dunja$$b2$$eEditor
000891374 7001_ $$0P:(DE-HGF)0$$aSaunders, Craig$$b3$$eEditor
000891374 7001_ $$0P:(DE-HGF)0$$aVan Hoecke, Sofie$$b4$$eEditor
000891374 7001_ $$0P:(DE-Juel1)177823$$aMore, Shammi$$b5
000891374 7001_ $$0P:(DE-Juel1)131678$$aEickhoff, Simon B.$$b6
000891374 7001_ $$0P:(DE-Juel1)144344$$aCaspers, Julian$$b7
000891374 7001_ $$0P:(DE-Juel1)172843$$aPatil, Kaustubh R.$$b8$$eCorresponding author
000891374 773__ $$a10.1007/978-3-030-67670-4_1
000891374 8564_ $$uhttps://juser.fz-juelich.de/record/891374/files/Invoice_2936161833.pdf
000891374 8564_ $$uhttps://juser.fz-juelich.de/record/891374/files/More2021_Chapter_ConfoundRemovalAndNormalizatio.pdf$$yOpenAccess
000891374 8767_ $$82936161833$$92021-02-09$$d2021-03-25$$eAPC$$jZahlung erfolgt$$zBelegnr. 1200165113 / 2021
000891374 909CO $$ooai:juser.fz-juelich.de:891374$$pdnbdelivery$$popenCost$$pVDB$$pdriver$$pOpenAPC$$popen_access$$popenaire
000891374 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)177823$$aForschungszentrum Jülich$$b5$$kFZJ
000891374 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)131678$$aForschungszentrum Jülich$$b6$$kFZJ
000891374 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)172843$$aForschungszentrum Jülich$$b8$$kFZJ
000891374 9130_ $$0G:(DE-HGF)POF3-571$$1G:(DE-HGF)POF3-570$$2G:(DE-HGF)POF3-500$$3G:(DE-HGF)POF3$$4G:(DE-HGF)POF$$aDE-HGF$$bKey Technologies$$lDecoding the Human Brain$$vConnectivity and Activity$$x0
000891374 9130_ $$0G:(DE-HGF)POF3-574$$1G:(DE-HGF)POF3-570$$2G:(DE-HGF)POF3-500$$3G:(DE-HGF)POF3$$4G:(DE-HGF)POF$$aDE-HGF$$bKey Technologies$$lDecoding the Human Brain$$vTheory, modelling and simulation$$x1
000891374 9131_ $$0G:(DE-HGF)POF4-525$$1G:(DE-HGF)POF4-520$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$aDE-HGF$$bKey Technologies$$lNatural, Artificial and Cognitive Information Processing$$vDecoding Brain Organization and Dysfunction$$x0
000891374 9141_ $$y2021
000891374 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2020-08-25
000891374 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000891374 915__ $$0StatID:(DE-HGF)0420$$2StatID$$aNationallizenz$$d2020-08-25$$wger
000891374 9201_ $$0I:(DE-Juel1)INM-7-20090406$$kINM-7$$lGehirn & Verhalten$$x0
000891374 980__ $$acontb
000891374 980__ $$aVDB
000891374 980__ $$aUNRESTRICTED
000891374 980__ $$aI:(DE-Juel1)INM-7-20090406
000891374 980__ $$aAPC
000891374 9801_ $$aAPC
000891374 9801_ $$aFullTexts