TY  - CONF
AU  - Schacht, Benedict
AU  - Greving, Imke
AU  - Frintrop, Simone
AU  - Zeller-Plumhoff, Berit
AU  - Wilms, Christian
TI  - Contextloss: Context Information for Topology-Preserving Segmentation
CY  - [Piscataway, NJ]
PB  - IEEE
M1  - PUBDB-2025-04532
SN  - 979-8-3315-2379-4
SP  - 1882 - 1887
PY  - 2025
N1  - "This year's ICIP theme is 'Image processing in the age of GenAI'" - Vorwort; Literaturangaben;
AB  - In 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 </td><td width="150">
AB  -  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 
T2  - 2025 IEEE International Conference on Image Processing
CY  - 14 Sep 2025 - 17 Sep 2025, Anchorage (AK)
Y2  - 14 Sep 2025 - 17 Sep 2025
M2  - Anchorage, AK
LB  - PUB:(DE-HGF)8 ; PUB:(DE-HGF)7
DO  - DOI:10.1109/ICIP55913.2025.11084563
UR  - https://bib-pubdb1.desy.de/record/639444
ER  -