Matches in SemOpenAlex for { <https://semopenalex.org/work/W4317832372> ?p ?o ?g. }
- W4317832372 abstract "Extracting hepatic vessels from abdominal images is of high interest for clinicians since it allows to divide the liver into functionally-independent Couinaud segments. In this respect, an automated liver blood vessel extraction is widely summoned. Despite the significant growth in performance of semantic segmentation methodologies, preserving the complex multi-scale geometry of main vessels and ramifications remains a major challenge. This paper provides a new deep supervised approach for vessel segmentation, with a strong focus on representations arising from the different scales inherent to the vascular tree geometry. In particular, we propose a new clustering technique to decompose the tree into various scale levels, from tiny to large vessels. Then, we extend standard 3D UNet to multi-task learning by incorporating scale-specific auxiliary tasks and contrastive learning to encourage the discrimination between scales in the shared representation. Promising results, depicted in several evaluation metrics, are revealed on the public 3D-IRCADb dataset." @default.
- W4317832372 created "2023-01-24" @default.
- W4317832372 creator A5017138072 @default.
- W4317832372 creator A5040529738 @default.
- W4317832372 creator A5044010357 @default.
- W4317832372 creator A5049686051 @default.
- W4317832372 creator A5061495694 @default.
- W4317832372 creator A5062019642 @default.
- W4317832372 creator A5083318519 @default.
- W4317832372 date "2023-04-18" @default.
- W4317832372 modified "2023-09-27" @default.
- W4317832372 title "Scale-Specific Auxiliary Multi-Task Contrastive Learning for Deep Liver Vessel Segmentation" @default.
- W4317832372 cites W1903029394 @default.
- W4317832372 cites W2048733914 @default.
- W4317832372 cites W2129534965 @default.
- W4317832372 cites W2800949106 @default.
- W4317832372 cites W2949676527 @default.
- W4317832372 cites W3002569343 @default.
- W4317832372 cites W3085046840 @default.
- W4317832372 cites W3162505601 @default.
- W4317832372 cites W3174708193 @default.
- W4317832372 cites W4206416486 @default.
- W4317832372 cites W4283647060 @default.
- W4317832372 cites W4284888200 @default.
- W4317832372 cites W4286744416 @default.
- W4317832372 doi "https://doi.org/10.1109/isbi53787.2023.10230364" @default.
- W4317832372 hasPublicationYear "2023" @default.
- W4317832372 type Work @default.
- W4317832372 citedByCount "0" @default.
- W4317832372 crossrefType "proceedings-article" @default.
- W4317832372 hasAuthorship W4317832372A5017138072 @default.
- W4317832372 hasAuthorship W4317832372A5040529738 @default.
- W4317832372 hasAuthorship W4317832372A5044010357 @default.
- W4317832372 hasAuthorship W4317832372A5049686051 @default.
- W4317832372 hasAuthorship W4317832372A5061495694 @default.
- W4317832372 hasAuthorship W4317832372A5062019642 @default.
- W4317832372 hasAuthorship W4317832372A5083318519 @default.
- W4317832372 hasConcept C108583219 @default.
- W4317832372 hasConcept C113174947 @default.
- W4317832372 hasConcept C119857082 @default.
- W4317832372 hasConcept C120665830 @default.
- W4317832372 hasConcept C121332964 @default.
- W4317832372 hasConcept C124504099 @default.
- W4317832372 hasConcept C127413603 @default.
- W4317832372 hasConcept C134306372 @default.
- W4317832372 hasConcept C153180895 @default.
- W4317832372 hasConcept C154945302 @default.
- W4317832372 hasConcept C17744445 @default.
- W4317832372 hasConcept C192209626 @default.
- W4317832372 hasConcept C199539241 @default.
- W4317832372 hasConcept C201995342 @default.
- W4317832372 hasConcept C2776359362 @default.
- W4317832372 hasConcept C2778755073 @default.
- W4317832372 hasConcept C2780451532 @default.
- W4317832372 hasConcept C31972630 @default.
- W4317832372 hasConcept C33923547 @default.
- W4317832372 hasConcept C41008148 @default.
- W4317832372 hasConcept C62520636 @default.
- W4317832372 hasConcept C73555534 @default.
- W4317832372 hasConcept C89600930 @default.
- W4317832372 hasConcept C94625758 @default.
- W4317832372 hasConceptScore W4317832372C108583219 @default.
- W4317832372 hasConceptScore W4317832372C113174947 @default.
- W4317832372 hasConceptScore W4317832372C119857082 @default.
- W4317832372 hasConceptScore W4317832372C120665830 @default.
- W4317832372 hasConceptScore W4317832372C121332964 @default.
- W4317832372 hasConceptScore W4317832372C124504099 @default.
- W4317832372 hasConceptScore W4317832372C127413603 @default.
- W4317832372 hasConceptScore W4317832372C134306372 @default.
- W4317832372 hasConceptScore W4317832372C153180895 @default.
- W4317832372 hasConceptScore W4317832372C154945302 @default.
- W4317832372 hasConceptScore W4317832372C17744445 @default.
- W4317832372 hasConceptScore W4317832372C192209626 @default.
- W4317832372 hasConceptScore W4317832372C199539241 @default.
- W4317832372 hasConceptScore W4317832372C201995342 @default.
- W4317832372 hasConceptScore W4317832372C2776359362 @default.
- W4317832372 hasConceptScore W4317832372C2778755073 @default.
- W4317832372 hasConceptScore W4317832372C2780451532 @default.
- W4317832372 hasConceptScore W4317832372C31972630 @default.
- W4317832372 hasConceptScore W4317832372C33923547 @default.
- W4317832372 hasConceptScore W4317832372C41008148 @default.
- W4317832372 hasConceptScore W4317832372C62520636 @default.
- W4317832372 hasConceptScore W4317832372C73555534 @default.
- W4317832372 hasConceptScore W4317832372C89600930 @default.
- W4317832372 hasConceptScore W4317832372C94625758 @default.
- W4317832372 hasLocation W43178323721 @default.
- W4317832372 hasLocation W43178323722 @default.
- W4317832372 hasLocation W43178323723 @default.
- W4317832372 hasOpenAccess W4317832372 @default.
- W4317832372 hasPrimaryLocation W43178323721 @default.
- W4317832372 hasRelatedWork W1669643531 @default.
- W4317832372 hasRelatedWork W2005437358 @default.
- W4317832372 hasRelatedWork W2008656436 @default.
- W4317832372 hasRelatedWork W2517104666 @default.
- W4317832372 hasRelatedWork W2790662084 @default.
- W4317832372 hasRelatedWork W4223943233 @default.
- W4317832372 hasRelatedWork W4285827401 @default.
- W4317832372 hasRelatedWork W4312200629 @default.
- W4317832372 hasRelatedWork W4360585206 @default.
- W4317832372 hasRelatedWork W4380075502 @default.