001049628 001__ 1049628
001049628 005__ 20251217202229.0
001049628 0247_ $$2arXiv$$aarXiv:2503.22271
001049628 0247_ $$2datacite_doi$$a10.34734/FZJ-2025-05416
001049628 037__ $$aFZJ-2025-05416
001049628 088__ $$2arXiv$$aarXiv:2503.22271
001049628 1001_ $$0P:(DE-Juel1)200339$$aRathore, Omini$$b0$$eContributor$$ufzj
001049628 245__ $$aEfficient Epistemic Uncertainty Estimation in Cerebrovascular Segmentation
001049628 260__ $$c2025
001049628 3367_ $$0PUB:(DE-HGF)25$$2PUB:(DE-HGF)$$aPreprint$$bpreprint$$mpreprint$$s1765991623_17930
001049628 3367_ $$2ORCID$$aWORKING_PAPER
001049628 3367_ $$028$$2EndNote$$aElectronic Article
001049628 3367_ $$2DRIVER$$apreprint
001049628 3367_ $$2BibTeX$$aARTICLE
001049628 3367_ $$2DataCite$$aOutput Types/Working Paper
001049628 520__ $$aBrain vessel segmentation of MR scans is a critical step in the diagnosis of cerebrovascular diseases. Due to the fine vessel structure, manual vessel segmentation is time consuming. Therefore, automatic deep learning (DL) based segmentation techniques are intensively investigated. As conventional DL models yield a high complexity and lack an indication of decision reliability, they are often considered as not trustworthy. This work aims to increase trust in DL based models by incorporating epistemic uncertainty quantification into cerebrovascular segmentation models for the first time. By implementing an efficient ensemble model combining the advantages of Bayesian Approximation and Deep Ensembles, we aim to overcome the high computational costs of conventional probabilistic networks. Areas of high model uncertainty and erroneous predictions are aligned which demonstrates the effectiveness and reliability of the approach. We perform extensive experiments applying the ensemble model on out-of-distribution (OOD) data. We demonstrate that for OOD-images, the estimated uncertainty increases. Additionally, omitting highly uncertain areas improves the segmentation quality, both for in- and out-of-distribution data. The ensemble model explains its limitations in a reliable manner and can maintain trustworthiness also for OOD data and could be considered in clinical applications
001049628 536__ $$0G:(DE-HGF)POF4-5112$$a5112 - Cross-Domain Algorithms, Tools, Methods Labs (ATMLs) and Research Groups (POF4-511)$$cPOF4-511$$fPOF IV$$x0
001049628 588__ $$aDataset connected to DataCite
001049628 7001_ $$0P:(DE-Juel1)175101$$aPaul, Richard Dominik$$b1$$eCollaboration author$$ufzj
001049628 7001_ $$0P:(DE-Juel1)151166$$aMorrison, Abigail$$b2$$eThesis advisor$$ufzj
001049628 7001_ $$0P:(DE-Juel1)129394$$aScharr, Hanno$$b3$$eThesis advisor$$ufzj
001049628 7001_ $$0P:(DE-Juel1)191494$$aPfaehler, Elisabeth$$b4$$eCorresponding author$$ufzj
001049628 8564_ $$uhttps://juser.fz-juelich.de/record/1049628/files/arxiv.pdf$$yOpenAccess
001049628 909CO $$ooai:juser.fz-juelich.de:1049628$$popenaire$$popen_access$$pVDB$$pdriver$$pdnbdelivery
001049628 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)200339$$aForschungszentrum Jülich$$b0$$kFZJ
001049628 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)175101$$aForschungszentrum Jülich$$b1$$kFZJ
001049628 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)151166$$aForschungszentrum Jülich$$b2$$kFZJ
001049628 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)129394$$aForschungszentrum Jülich$$b3$$kFZJ
001049628 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)191494$$aForschungszentrum Jülich$$b4$$kFZJ
001049628 9131_ $$0G:(DE-HGF)POF4-511$$1G:(DE-HGF)POF4-510$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5112$$aDE-HGF$$bKey Technologies$$lEngineering Digital Futures – Supercomputing, Data Management and Information Security for Knowledge and Action$$vEnabling Computational- & Data-Intensive Science and Engineering$$x0
001049628 9141_ $$y2025
001049628 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001049628 920__ $$lyes
001049628 9201_ $$0I:(DE-Juel1)IAS-8-20210421$$kIAS-8$$lDatenanalyse und Maschinenlernen$$x0
001049628 980__ $$apreprint
001049628 980__ $$aVDB
001049628 980__ $$aUNRESTRICTED
001049628 980__ $$aI:(DE-Juel1)IAS-8-20210421
001049628 9801_ $$aFullTexts