Matches in SemOpenAlex for { <https://semopenalex.org/work/W3207601934> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W3207601934 endingPage "102258" @default.
- W3207601934 startingPage "102258" @default.
- W3207601934 abstract "In this paper, we address the problem of fully automatic labeling and segmentation of 3D vertebrae in arbitrary Field-Of-View (FOV) CT images. We propose a deep learning-based two-stage solution to tackle these two problems. More specifically, in the first stage, the challenging vertebra labeling problem is solved via a novel transformers-based 3D object detector that views automatic detection of vertebrae in arbitrary FOV CT scans as a one-to-one set prediction problem. The main components of the new method, called Spine-Transformers, are a one-to-one set based global loss that forces unique predictions and a light-weighted 3D transformer architecture equipped with a skip connection and learnable positional embeddings for encoder and decoder, respectively. We additionally propose an inscribed sphere-based object detector to replace the regular box-based object detector for a better handling of volume orientation variations. Our method reasons about the relationships of different levels of vertebrae and the global volume context to directly infer all vertebrae in parallel. In the second stage, the segmentation of the identified vertebrae and the refinement of the detected centers are then done by training one single multi-task encoder-decoder network for all vertebrae as the network does not need to identify which vertebra it is working on. The two tasks share a common encoder path but with different decoder paths. Comprehensive experiments are conducted on two public datasets and one in-house dataset. The experimental results demonstrate the efficacy of the present approach." @default.
- W3207601934 created "2021-10-25" @default.
- W3207601934 creator A5057420536 @default.
- W3207601934 creator A5088035307 @default.
- W3207601934 creator A5091784924 @default.
- W3207601934 date "2022-01-01" @default.
- W3207601934 modified "2023-09-30" @default.
- W3207601934 title "Spine-transformers: Vertebra labeling and segmentation in arbitrary field-of-view spine CTs via 3D transformers" @default.
- W3207601934 cites W1979064019 @default.
- W3207601934 cites W1986323513 @default.
- W3207601934 cites W2060499860 @default.
- W3207601934 cites W2064675550 @default.
- W3207601934 cites W2065812187 @default.
- W3207601934 cites W2068854578 @default.
- W3207601934 cites W2075358081 @default.
- W3207601934 cites W2091904383 @default.
- W3207601934 cites W2165014123 @default.
- W3207601934 cites W2222318341 @default.
- W3207601934 cites W2222512263 @default.
- W3207601934 cites W2901559346 @default.
- W3207601934 cites W2919115771 @default.
- W3207601934 cites W2925288829 @default.
- W3207601934 cites W2952939839 @default.
- W3207601934 cites W2957485116 @default.
- W3207601934 cites W2960131585 @default.
- W3207601934 cites W3000180983 @default.
- W3207601934 cites W3046053509 @default.
- W3207601934 cites W3087644100 @default.
- W3207601934 cites W3103005696 @default.
- W3207601934 cites W3107331169 @default.
- W3207601934 cites W3112346810 @default.
- W3207601934 cites W4206706211 @default.
- W3207601934 doi "https://doi.org/10.1016/j.media.2021.102258" @default.
- W3207601934 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34670147" @default.
- W3207601934 hasPublicationYear "2022" @default.
- W3207601934 type Work @default.
- W3207601934 sameAs 3207601934 @default.
- W3207601934 citedByCount "18" @default.
- W3207601934 countsByYear W32076019342022 @default.
- W3207601934 countsByYear W32076019342023 @default.
- W3207601934 crossrefType "journal-article" @default.
- W3207601934 hasAuthorship W3207601934A5057420536 @default.
- W3207601934 hasAuthorship W3207601934A5088035307 @default.
- W3207601934 hasAuthorship W3207601934A5091784924 @default.
- W3207601934 hasConcept C105702510 @default.
- W3207601934 hasConcept C111919701 @default.
- W3207601934 hasConcept C118505674 @default.
- W3207601934 hasConcept C119599485 @default.
- W3207601934 hasConcept C127413603 @default.
- W3207601934 hasConcept C153180895 @default.
- W3207601934 hasConcept C154945302 @default.
- W3207601934 hasConcept C165801399 @default.
- W3207601934 hasConcept C2776412215 @default.
- W3207601934 hasConcept C31972630 @default.
- W3207601934 hasConcept C41008148 @default.
- W3207601934 hasConcept C66322947 @default.
- W3207601934 hasConcept C71924100 @default.
- W3207601934 hasConcept C89600930 @default.
- W3207601934 hasConceptScore W3207601934C105702510 @default.
- W3207601934 hasConceptScore W3207601934C111919701 @default.
- W3207601934 hasConceptScore W3207601934C118505674 @default.
- W3207601934 hasConceptScore W3207601934C119599485 @default.
- W3207601934 hasConceptScore W3207601934C127413603 @default.
- W3207601934 hasConceptScore W3207601934C153180895 @default.
- W3207601934 hasConceptScore W3207601934C154945302 @default.
- W3207601934 hasConceptScore W3207601934C165801399 @default.
- W3207601934 hasConceptScore W3207601934C2776412215 @default.
- W3207601934 hasConceptScore W3207601934C31972630 @default.
- W3207601934 hasConceptScore W3207601934C41008148 @default.
- W3207601934 hasConceptScore W3207601934C66322947 @default.
- W3207601934 hasConceptScore W3207601934C71924100 @default.
- W3207601934 hasConceptScore W3207601934C89600930 @default.
- W3207601934 hasFunder F4320321001 @default.
- W3207601934 hasFunder F4320321885 @default.
- W3207601934 hasFunder F4320335777 @default.
- W3207601934 hasFunder F4320336026 @default.
- W3207601934 hasLocation W32076019341 @default.
- W3207601934 hasLocation W32076019342 @default.
- W3207601934 hasOpenAccess W3207601934 @default.
- W3207601934 hasPrimaryLocation W32076019341 @default.
- W3207601934 hasRelatedWork W1669643531 @default.
- W3207601934 hasRelatedWork W2005437358 @default.
- W3207601934 hasRelatedWork W2008656436 @default.
- W3207601934 hasRelatedWork W2023558673 @default.
- W3207601934 hasRelatedWork W2039154422 @default.
- W3207601934 hasRelatedWork W2110230079 @default.
- W3207601934 hasRelatedWork W2122581818 @default.
- W3207601934 hasRelatedWork W2134924024 @default.
- W3207601934 hasRelatedWork W2517104666 @default.
- W3207601934 hasRelatedWork W2182382398 @default.
- W3207601934 hasVolume "75" @default.
- W3207601934 isParatext "false" @default.
- W3207601934 isRetracted "false" @default.
- W3207601934 magId "3207601934" @default.
- W3207601934 workType "article" @default.