000639444 001__ 639444
000639444 005__ 20251119161937.0
000639444 020__ $$a979-8-3315-2379-4
000639444 0247_ $$2doi$$a10.1109/ICIP55913.2025.11084563
000639444 0247_ $$2openalex$$aopenalex:W4413278095
000639444 037__ $$aPUBDB-2025-04532
000639444 041__ $$aEnglish
000639444 1001_ $$0P:(DE-H253)PIP1029844$$aSchacht, Benedict$$b0
000639444 1112_ $$a2025 IEEE International Conference on Image Processing$$cAnchorage$$d2025-09-14 - 2025-09-17$$g(ICIP)$$wAK
000639444 245__ $$aContextloss: Context Information for Topology-Preserving Segmentation
000639444 260__ $$a[Piscataway, NJ]$$bIEEE$$c2025
000639444 29510 $$a[Ebook] 2025 IEEE International Conference on Image Processing (ICIP) : proceedings : 14-17 September 2025, Anchorage, Alaska, United States / sponsored by: the Institute of Electrical and Electronics Engineers, Signal Processing Society , [Piscataway, NJ] : IEEE, 2025,
000639444 300__ $$a1882 - 1887
000639444 3367_ $$2ORCID$$aCONFERENCE_PAPER
000639444 3367_ $$033$$2EndNote$$aConference Paper
000639444 3367_ $$2BibTeX$$aINPROCEEDINGS
000639444 3367_ $$2DRIVER$$aconferenceObject
000639444 3367_ $$2DataCite$$aOutput Types/Conference Paper
000639444 3367_ $$0PUB:(DE-HGF)8$$2PUB:(DE-HGF)$$aContribution to a conference proceedings$$bcontrib$$mcontrib$$s1762857902_1868922
000639444 3367_ $$0PUB:(DE-HGF)7$$2PUB:(DE-HGF)$$aContribution to a book$$mcontb
000639444 500__ $$a"This year's ICIP theme is 'Image processing in the age of GenAI'" - Vorwort; Literaturangaben;
000639444 520__ $$aIn image segmentation, preserving the topology of segmented structures like vessels, membranes, or roads is crucial. For instance, topological errors on road networks can significantly impact navigation. Recently proposed solutions are loss functions based on critical pixel masks that consider the whole skeleton of the segmented structures in the critical pixel mask. We propose the novel loss function ContextLoss (CLoss) that improves topological correctness by considering topological errors with their whole context in the critical pixel mask. The additional context improves the network focus on the topological errors. Further, we propose two intuitive metrics to verify improved connectivity due to a closing of missed connections. We benchmark our proposed CLoss on three public datasets (2D & 3D) and our own 3D nano-imaging dataset of bone cement lines. Training with our proposed CLoss increases performance on topology-aware metrics and repairs up to 44 % more missed connections than other state-of-the-art methods. We make the code publicly available1 2. 
000639444 536__ $$0G:(DE-HGF)POF4-6G3$$a6G3 - PETRA III (DESY) (POF4-6G3)$$cPOF4-6G3$$fPOF IV$$x0
000639444 536__ $$0G:(DE-HGF)2019_IVF-HIDSS-0002$$aHIDSS-0002 - DASHH: Data Science in Hamburg - Helmholtz Graduate School for the Structure of Matter (2019_IVF-HIDSS-0002)$$c2019_IVF-HIDSS-0002$$x1
000639444 588__ $$aDataset connected to CrossRef Conference
000639444 693__ $$0EXP:(DE-H253)P-P05-20150101$$1EXP:(DE-H253)PETRAIII-20150101$$6EXP:(DE-H253)P-P05-20150101$$aPETRA III$$fPETRA Beamline P05$$x0
000639444 7001_ $$0P:(DE-H253)PIP1009579$$aGreving, Imke$$b1
000639444 7001_ $$aFrintrop, Simone$$b2
000639444 7001_ $$0P:(DE-H253)PIP1031548$$aZeller-Plumhoff, Berit$$b3
000639444 7001_ $$aWilms, Christian$$b4
000639444 773__ $$a10.1109/ICIP55913.2025.11084563
000639444 8564_ $$uhttps://bib-pubdb1.desy.de/record/639444/files/Schacht-2025-Contextloss_%20Context%20Information.pdf$$yRestricted
000639444 8564_ $$uhttps://bib-pubdb1.desy.de/record/639444/files/Schacht-2025-Contextloss_%20Context%20Information.pdf?subformat=pdfa$$xpdfa$$yRestricted
000639444 909CO $$ooai:bib-pubdb1.desy.de:639444$$pVDB
000639444 9101_ $$0I:(DE-HGF)0$$6P:(DE-H253)PIP1029844$$aExternal Institute$$b0$$kExtern
000639444 9101_ $$0I:(DE-588b)1231250402$$6P:(DE-H253)PIP1029844$$aHelmholtz-Zentrum Hereon$$b0$$kHereon
000639444 9101_ $$0I:(DE-588b)16087541-9$$6P:(DE-H253)PIP1009579$$aHelmholtz-Zentrum Geesthacht$$b1$$kHZG
000639444 9101_ $$0I:(DE-588b)1231250402$$6P:(DE-H253)PIP1009579$$aHelmholtz-Zentrum Hereon$$b1$$kHereon
000639444 9101_ $$0I:(DE-588b)16087541-9$$6P:(DE-H253)PIP1031548$$aHelmholtz-Zentrum Geesthacht$$b3$$kHZG
000639444 9101_ $$0I:(DE-588b)1231250402$$6P:(DE-H253)PIP1031548$$aHelmholtz-Zentrum Hereon$$b3$$kHereon
000639444 9131_ $$0G:(DE-HGF)POF4-6G3$$1G:(DE-HGF)POF4-6G0$$2G:(DE-HGF)POF4-600$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$aDE-HGF$$bForschungsbereich Materie$$lGroßgeräte: Materie$$vPETRA III (DESY)$$x0
000639444 9141_ $$y2025
000639444 9201_ $$0I:(DE-H253)Hereon-20210428$$kHereon$$lHelmholtz-Zentrum Hereon$$x0
000639444 9201_ $$0I:(DE-H253)HAS-User-20120731$$kDOOR ; HAS-User$$lDOOR-User$$x1
000639444 980__ $$acontrib
000639444 980__ $$aVDB
000639444 980__ $$acontb
000639444 980__ $$aI:(DE-H253)Hereon-20210428
000639444 980__ $$aI:(DE-H253)HAS-User-20120731
000639444 980__ $$aUNRESTRICTED