001023471 001__ 1023471
001023471 005__ 20240220203048.0
001023471 0247_ $$2doi$$a10.48550/ARXIV.2401.17207
001023471 0247_ $$2datacite_doi$$a10.34734/FZJ-2024-01704
001023471 037__ $$aFZJ-2024-01704
001023471 1001_ $$0P:(DE-HGF)0$$aOberstrass, Alexander$$b0$$eCorresponding author
001023471 245__ $$aSelf-Supervised Representation Learning for Nerve Fiber Distribution Patterns in 3D-PLI
001023471 260__ $$barXiv$$c2024
001023471 3367_ $$0PUB:(DE-HGF)25$$2PUB:(DE-HGF)$$aPreprint$$bpreprint$$mpreprint$$s1708432351_7138
001023471 3367_ $$2ORCID$$aWORKING_PAPER
001023471 3367_ $$028$$2EndNote$$aElectronic Article
001023471 3367_ $$2DRIVER$$apreprint
001023471 3367_ $$2BibTeX$$aARTICLE
001023471 3367_ $$2DataCite$$aOutput Types/Working Paper
001023471 520__ $$aA comprehensive understanding of the organizational principles in the human brain requires, among other factors, well-quantifiable descriptors of nerve fiber architecture. Three-dimensional polarized light imaging (3D-PLI) is a microscopic imaging technique that enables insights into the fine-grained organization of myelinated nerve fibers with high resolution. Descriptors characterizing the fiber architecture observed in 3D-PLI would enable downstream analysis tasks such as multimodal correlation studies, clustering, and mapping. However, best practices for observer-independent characterization of fiber architecture in 3D-PLI are not yet available. To this end, we propose the application of a fully data-driven approach to characterize nerve fiber architecture in 3D-PLI images using self-supervised representation learning. We introduce a 3D-Context Contrastive Learning (CL-3D) objective that utilizes the spatial neighborhood of texture examples across histological brain sections of a 3D reconstructed volume to sample positive pairs for contrastive learning. We combine this sampling strategy with specifically designed image augmentations to gain robustness to typical variations in 3D-PLI parameter maps. The approach is demonstrated for the 3D reconstructed occipital lobe of a vervet monkey brain. We show that extracted features are highly sensitive to different configurations of nerve fibers, yet robust to variations between consecutive brain sections arising from histological processing. We demonstrate their practical applicability for retrieving clusters of homogeneous fiber architecture and performing data mining for interactively selected templates of specific components of fiber architecture such as U-fibers.
001023471 536__ $$0G:(DE-HGF)POF4-5254$$a5254 - Neuroscientific Data Analytics and AI (POF4-525)$$cPOF4-525$$fPOF IV$$x0
001023471 536__ $$0G:(DE-Juel-1)E.40401.62$$aHelmholtz AI - Helmholtz Artificial Intelligence  Coordination Unit – Local Unit FZJ (E.40401.62)$$cE.40401.62$$x1
001023471 536__ $$0G:(EU-Grant)945539$$aHBP SGA3 - Human Brain Project Specific Grant Agreement 3 (945539)$$c945539$$fH2020-SGA-FETFLAG-HBP-2019$$x2
001023471 536__ $$0G:(DE-Juel1)JL SMHB-2021-2027$$aJL SMHB - Joint Lab Supercomputing and Modeling for the Human Brain (JL SMHB-2021-2027)$$cJL SMHB-2021-2027$$x3
001023471 536__ $$0G:(DE-HGF)InterLabs-0015$$aHIBALL - Helmholtz International BigBrain Analytics and Learning Laboratory (HIBALL) (InterLabs-0015)$$cInterLabs-0015$$x4
001023471 588__ $$aDataset connected to DataCite
001023471 650_7 $$2Other$$aComputer Vision and Pattern Recognition (cs.CV)
001023471 650_7 $$2Other$$aFOS: Computer and information sciences
001023471 7001_ $$0P:(DE-HGF)0$$aMuenzing, Sascha E. A.$$b1
001023471 7001_ $$0P:(DE-Juel1)171512$$aNiu, Meiqi$$b2$$ufzj
001023471 7001_ $$0P:(DE-Juel1)131701$$aPalomero-Gallagher, Nicola$$b3$$ufzj
001023471 7001_ $$0P:(DE-Juel1)170068$$aSchiffer, Christian$$b4$$ufzj
001023471 7001_ $$0P:(DE-Juel1)131632$$aAxer, Markus$$b5$$ufzj
001023471 7001_ $$0P:(DE-Juel1)131631$$aAmunts, Katrin$$b6$$ufzj
001023471 7001_ $$0P:(DE-Juel1)165746$$aDickscheid, Timo$$b7$$ufzj
001023471 773__ $$a10.48550/ARXIV.2401.17207
001023471 8564_ $$uhttps://juser.fz-juelich.de/record/1023471/files/Oberstrass_arXiv_10.48550.arxiv.2101.17207.pdf$$yOpenAccess
001023471 8564_ $$uhttps://juser.fz-juelich.de/record/1023471/files/Oberstrass_arXiv_10.48550.arxiv.2101.17207.gif?subformat=icon$$xicon$$yOpenAccess
001023471 8564_ $$uhttps://juser.fz-juelich.de/record/1023471/files/Oberstrass_arXiv_10.48550.arxiv.2101.17207.jpg?subformat=icon-1440$$xicon-1440$$yOpenAccess
001023471 8564_ $$uhttps://juser.fz-juelich.de/record/1023471/files/Oberstrass_arXiv_10.48550.arxiv.2101.17207.jpg?subformat=icon-180$$xicon-180$$yOpenAccess
001023471 8564_ $$uhttps://juser.fz-juelich.de/record/1023471/files/Oberstrass_arXiv_10.48550.arxiv.2101.17207.jpg?subformat=icon-640$$xicon-640$$yOpenAccess
001023471 909CO $$ooai:juser.fz-juelich.de:1023471$$popenaire$$popen_access$$pdriver$$pVDB$$pec_fundedresources$$pdnbdelivery
001023471 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)171512$$aForschungszentrum Jülich$$b2$$kFZJ
001023471 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)131701$$aForschungszentrum Jülich$$b3$$kFZJ
001023471 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)170068$$aForschungszentrum Jülich$$b4$$kFZJ
001023471 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)131632$$aForschungszentrum Jülich$$b5$$kFZJ
001023471 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)131631$$aForschungszentrum Jülich$$b6$$kFZJ
001023471 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)165746$$aForschungszentrum Jülich$$b7$$kFZJ
001023471 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$$x0
001023471 9141_ $$y2024
001023471 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001023471 9201_ $$0I:(DE-Juel1)INM-1-20090406$$kINM-1$$lStrukturelle und funktionelle Organisation des Gehirns$$x0
001023471 980__ $$apreprint
001023471 980__ $$aVDB
001023471 980__ $$aUNRESTRICTED
001023471 980__ $$aI:(DE-Juel1)INM-1-20090406
001023471 9801_ $$aFullTexts