Medizinische Universität Graz Austria/Österreich - Forschungsportal - Medical University of Graz
Gewählte Publikation:
SHR Neuro Krebs Kardio Lipid Stoffw Microb
Oner, D; Garin, A; Kozinski, M; Hess, K; Fua, P.
Persistent Homology With Improved Locality Information for More Effective Delineation.
IEEE Trans Pattern Anal Mach Intell. 2023; 45(8): 10588-10595.
Doi: 10.1109/TPAMI.2023.3246921
Web of Science
PubMed
FullText
FullText_MUG
- Führende Autor*innen der Med Uni Graz
- Kozinski Mateusz
- Altmetrics:
- Dimensions Citations:
- Plum Analytics:
- Scite (citation analytics):
- Abstract:
- Persistent Homology (PH) has been successfully used to train networks to detect curvilinear structures and to improve the topological quality of their results. However, existing methods are very global and ignore the location of topological features. In this paper, we remedy this by introducing a new filtration function that fuses two earlier approaches: thresholding-based filtration, previously used to train deep networks to segment medical images, and filtration with height functions, typically used to compare 2D and 3D shapes. We experimentally demonstrate that deep networks trained using our PH-based loss function yield reconstructions of road networks and neuronal processes that reflect ground-truth connectivity better than networks trained with existing loss functions based on PH.
- Find related publications in this database (Keywords)
- Aerial images
- connectivity
- map reconstruction
- road network reconstruction