001030924 001__ 1030924
001030924 005__ 20250912110159.0
001030924 0247_ $$2doi$$a10.1162/imag_a_00251
001030924 0247_ $$2datacite_doi$$a10.34734/FZJ-2024-05517
001030924 0247_ $$2pmid$$a40800257
001030924 0247_ $$2WOS$$aWOS:001531565300003
001030924 037__ $$aFZJ-2024-05517
001030924 082__ $$a050
001030924 1001_ $$0P:(DE-HGF)0$$aWulan, Naren$$b0
001030924 245__ $$aTranslating phenotypic prediction models from big to small anatomical MRI data using meta-matching
001030924 260__ $$aCambridge, MA$$bMIT Press$$c2024
001030924 3367_ $$2DRIVER$$aarticle
001030924 3367_ $$2DataCite$$aOutput Types/Journal article
001030924 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1737100324_7619
001030924 3367_ $$2BibTeX$$aARTICLE
001030924 3367_ $$2ORCID$$aJOURNAL_ARTICLE
001030924 3367_ $$00$$2EndNote$$aJournal Article
001030924 520__ $$aIndividualized phenotypic prediction based on structural magnetic resonance imaging (MRI) is an important goal in neuroscience. Prediction performance increases with larger samples, but small-scale datasets with fewer than 200 participants are often unavoidable. We have previously proposed a “meta-matching” framework to translate models trained from large datasets to improve the prediction of new unseen phenotypes in small collection efforts. Meta-matching exploits correlations between phenotypes, yielding large improvement over classical machine learning when applied to prediction models using resting-state functional connectivity as input features. Here, we adapt the two best performing meta-matching variants (“meta-matching finetune” and “meta-matching stacking”) from our previous study to work with T1-weighted MRI data by changing the base neural network architecture to a 3D convolution neural network. We compare the two meta-matching variants with elastic net and classical transfer learning using the UK Biobank (N = 36,461), the Human Connectome Project Young Adults (HCP-YA) dataset (N = 1,017), and the HCP-Aging dataset (N = 656). We find that meta-matching outperforms elastic net and classical transfer learning by a large margin, both when translating models within the same dataset and when translating models across datasets with different MRI scanners, acquisition protocols, and demographics. For example, when translating a UK Biobank model to 100 HCP-YA participants, meta-matching finetune yielded a 136% improvement in variance explained over transfer learning, with an average absolute gain of 2.6% (minimum = –0.9%, maximum = 17.6%) across 35 phenotypes. Overall, our results highlight the versatility of the meta-matching framework.
001030924 536__ $$0G:(DE-HGF)POF4-5254$$a5254 - Neuroscientific Data Analytics and AI (POF4-525)$$cPOF4-525$$fPOF IV$$x0
001030924 536__ $$0G:(DE-HGF)POF4-5252$$a5252 - Brain Dysfunction and Plasticity (POF4-525)$$cPOF4-525$$fPOF IV$$x1
001030924 588__ $$aDataset connected to CrossRef, Journals: juser.fz-juelich.de
001030924 7001_ $$0P:(DE-HGF)0$$aAn, Lijun$$b1
001030924 7001_ $$0P:(DE-HGF)0$$aZhang, Chen$$b2
001030924 7001_ $$0P:(DE-HGF)0$$aKong, Ru$$b3
001030924 7001_ $$0P:(DE-HGF)0$$aChen, Pansheng$$b4
001030924 7001_ $$0P:(DE-HGF)0$$aBzdok, Danilo$$b5
001030924 7001_ $$0P:(DE-Juel1)131678$$aEickhoff, Simon B.$$b6$$ufzj
001030924 7001_ $$0P:(DE-HGF)0$$aHolmes, Avram J.$$b7
001030924 7001_ $$0P:(DE-HGF)0$$aYeo, B. T. Thomas$$b8$$eCorresponding author
001030924 773__ $$0PERI:(DE-600)3167925-0$$a10.1162/imag_a_00251$$gVol. 2, p. 1 - 21$$p1 - 21$$tImaging neuroscience$$v2$$x2837-6056$$y2024
001030924 8564_ $$uhttps://juser.fz-juelich.de/record/1030924/files/imag_a_00251.pdf$$yOpenAccess
001030924 909CO $$ooai:juser.fz-juelich.de:1030924$$pdnbdelivery$$pdriver$$pVDB$$popen_access$$popenaire
001030924 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)131678$$aForschungszentrum Jülich$$b6$$kFZJ
001030924 9101_ $$0I:(DE-HGF)0$$6P:(DE-Juel1)131678$$a HHU Düsseldorf$$b6
001030924 9101_ $$0I:(DE-HGF)0$$6P:(DE-HGF)0$$a Department of Medicine, Human Potential Translational Research Programme & Institute for Digital Medicine (WisDM), Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore *Corresponding Author: B.T. Thomas Yeo (yeoyeo02+INau@gmail.com)$$b8
001030924 9131_ $$0G:(DE-HGF)POF4-525$$1G:(DE-HGF)POF4-520$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5254$$aDE-HGF$$bKey Technologies$$lNatural, Artificial and Cognitive Information Processing$$vDecoding Brain Organization and Dysfunction$$x0
001030924 9131_ $$0G:(DE-HGF)POF4-525$$1G:(DE-HGF)POF4-520$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5252$$aDE-HGF$$bKey Technologies$$lNatural, Artificial and Cognitive Information Processing$$vDecoding Brain Organization and Dysfunction$$x1
001030924 9141_ $$y2024
001030924 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001030924 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
001030924 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2025-01-02
001030924 915__ $$0StatID:(DE-HGF)0501$$2StatID$$aDBCoverage$$bDOAJ Seal$$d2024-09-26T09:40:26Z
001030924 915__ $$0StatID:(DE-HGF)0500$$2StatID$$aDBCoverage$$bDOAJ$$d2024-09-26T09:40:26Z
001030924 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bDOAJ : Anonymous peer review$$d2024-09-26T09:40:26Z
001030924 9201_ $$0I:(DE-Juel1)INM-7-20090406$$kINM-7$$lGehirn & Verhalten$$x0
001030924 9801_ $$aFullTexts
001030924 980__ $$ajournal
001030924 980__ $$aVDB
001030924 980__ $$aUNRESTRICTED
001030924 980__ $$aI:(DE-Juel1)INM-7-20090406