Contribution to a conference proceedings/Contribution to a book PUBDB-2025-04532

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png
Contextloss: Context Information for Topology-Preserving Segmentation

 ;  ;  ;  ;

2025
IEEE [Piscataway, NJ]
ISBN: 979-8-3315-2379-4

[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,
2025 IEEE International Conference on Image Processing, (ICIP), AnchorageAnchorage, AK, 14 Sep 2025 - 17 Sep 20252025-09-142025-09-17
[Piscataway, NJ] : IEEE 1882 - 1887 () [10.1109/ICIP55913.2025.11084563]  GO

This record in other databases:    

Please use a persistent id in citations: doi:

Abstract: 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 & 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.


Note: "This year's ICIP theme is 'Image processing in the age of GenAI'" - Vorwort; Literaturangaben;

Contributing Institute(s):
  1. Helmholtz-Zentrum Hereon (Hereon)
  2. DOOR-User (DOOR ; HAS-User)
Research Program(s):
  1. 6G3 - PETRA III (DESY) (POF4-6G3) (POF4-6G3)
  2. HIDSS-0002 - DASHH: Data Science in Hamburg - Helmholtz Graduate School for the Structure of Matter (2019_IVF-HIDSS-0002) (2019_IVF-HIDSS-0002)
Experiment(s):
  1. PETRA Beamline P05 (PETRA III)

Appears in the scientific report 2025
Click to display QR Code for this record

The record appears in these collections:
Private Collections > >Extern > >HAS-User > HAS-User
Document types > Events > Contributions to a conference proceedings
Document types > Books > Contribution to a book
Private Collections > >Hereon > Hereon
Public records
Publications database

 Record created 2025-10-22, last modified 2025-11-19


Restricted:
Download fulltext PDF Download fulltext PDF (PDFA)
Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)