001043522 001__ 1043522
001043522 005__ 20250717202250.0
001043522 0247_ $$2datacite_doi$$a10.34734/FZJ-2025-02898
001043522 037__ $$aFZJ-2025-02898
001043522 041__ $$aEnglish
001043522 1001_ $$0P:(DE-Juel1)198947$$aBoztoprak, Zeynep$$b0$$eCorresponding author$$ufzj
001043522 1112_ $$aHelmholtz Imaging Conference 2025$$cPotsdam$$d2025-06-26 - 2025-06-28$$wGermany
001043522 245__ $$aSpatial Contrastive Learning for Anchoring Histological Human Brain Sections Within a Reference 3D Model
001043522 260__ $$c2025
001043522 3367_ $$033$$2EndNote$$aConference Paper
001043522 3367_ $$2BibTeX$$aINPROCEEDINGS
001043522 3367_ $$2DRIVER$$aconferenceObject
001043522 3367_ $$2ORCID$$aCONFERENCE_POSTER
001043522 3367_ $$2DataCite$$aOutput Types/Conference Poster
001043522 3367_ $$0PUB:(DE-HGF)24$$2PUB:(DE-HGF)$$aPoster$$bposter$$mposter$$s1752732246_21156$$xAfter Call
001043522 520__ $$aAnalyzing the structural organization of the human brain involves the study of nerve fibers that connect neurons and whole brain regions. In addition, a deeper knowledge of the arrangement of these anatomical connections, also known as connectome, contributes to a better understanding of how the brain processes information. 3D Polarized Light Imaging (3D-PLI) exploits the birefringence of the myelin sheath to visualize short- and long-range single nerve fibers and fiber bundles, providing detailed images of fiber organization at the microscopic level. However, analyzing and interpreting the large amounts of complex data is time-consuming and requires expert knowledge. Since the complexity of nerve fiber organization is difficult to capture in a scalable manner using traditional feature extraction methods, we propose a data-driven approach to learn characteristic features of fiber architecture.We train a deep neural network to map high-resolution image patches extracted from 3D-PLI sections to feature vectors that encode the fiber architectonic properties in the image patch.The model is trained on 500.000 patches (size 2048x2048 px at 2.66 um/px) from 26 3D-PLI human brain sections using a contrastive learning approach. The method is based on the assumption that spatially close image patches have more structural similarity than more distant pairs. The idea is to train a neural network that pulls feature representations of similar inputs closer together and pushes those of dissimilar inputs apart in feature space. Similarity between two image patches is computed using the Radial Basis Function (RBF) kernel applied to the Euclidean distance between their corresponding 3D brain coordinates.Our analysis shows that clustering in latent space reveals distinctions between subcortical regions and remaining tissue, and that atlas labeling reveals a grouping of structures that aligns with brain regions and fiber bundles. Evaluating coordinate regression and spatial anchoring tasks demonstrates that the learned features better preserve spatial relationships and achieve lower Mean-Squared-Error (MSE) than classical texture features. These results demonstrate that the learned representations encode nerve fiber properties and structural information, providing an important foundation for developing scalable analysis methods for fiber architecture in the human brain.
001043522 536__ $$0G:(DE-HGF)POF4-5254$$a5254 - Neuroscientific Data Analytics and AI (POF4-525)$$cPOF4-525$$fPOF IV$$x0
001043522 536__ $$0G:(DE-HGF)ZT-I-PF-4-061$$aX-BRAIN (ZT-I-PF-4-061)$$cZT-I-PF-4-061$$x1
001043522 536__ $$0G:(DE-Juel-1)E.40401.62$$aHelmholtz AI - Helmholtz Artificial Intelligence  Coordination Unit – Local Unit FZJ (E.40401.62)$$cE.40401.62$$x2
001043522 536__ $$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$$x3
001043522 536__ $$0G:(DE-HGF)InterLabs-0015$$aHIBALL - Helmholtz International BigBrain Analytics and Learning Laboratory (HIBALL) (InterLabs-0015)$$cInterLabs-0015$$x4
001043522 536__ $$0G:(EU-Grant)101147319$$aEBRAINS 2.0 - EBRAINS 2.0: A Research Infrastructure to Advance Neuroscience and Brain Health (101147319)$$c101147319$$fHORIZON-INFRA-2022-SERV-B-01$$x5
001043522 7001_ $$0P:(DE-Juel1)165746$$aDickscheid, Timo$$b1$$ufzj
001043522 7001_ $$0P:(DE-Juel1)131631$$aAmunts, Katrin$$b2$$ufzj
001043522 7001_ $$0P:(DE-Juel1)131632$$aAxer, Markus$$b3$$ufzj
001043522 7001_ $$0P:(DE-Juel1)170068$$aSchiffer, Christian$$b4$$ufzj
001043522 8564_ $$uhttps://juser.fz-juelich.de/record/1043522/files/2025_boztoprak_helmholtz_imaging.pdf$$yOpenAccess
001043522 909CO $$ooai:juser.fz-juelich.de:1043522$$pec_fundedresources$$pdriver$$pVDB$$popen_access$$popenaire
001043522 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)198947$$aForschungszentrum Jülich$$b0$$kFZJ
001043522 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)165746$$aForschungszentrum Jülich$$b1$$kFZJ
001043522 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)131631$$aForschungszentrum Jülich$$b2$$kFZJ
001043522 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)131632$$aForschungszentrum Jülich$$b3$$kFZJ
001043522 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)170068$$aForschungszentrum Jülich$$b4$$kFZJ
001043522 9131_ $$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
001043522 9141_ $$y2025
001043522 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001043522 920__ $$lyes
001043522 9201_ $$0I:(DE-Juel1)INM-1-20090406$$kINM-1$$lStrukturelle und funktionelle Organisation des Gehirns$$x0
001043522 980__ $$aposter
001043522 980__ $$aVDB
001043522 980__ $$aUNRESTRICTED
001043522 980__ $$aI:(DE-Juel1)INM-1-20090406
001043522 9801_ $$aFullTexts