Matches in SemOpenAlex for { <https://semopenalex.org/work/W3099683629> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W3099683629 endingPage "572" @default.
- W3099683629 startingPage "562" @default.
- W3099683629 abstract "This paper addresses a fundamental challenge in 3D medical image processing: how to deal with imaging thickness. For anisotropic medical volumes, there is a significant performance gap between thin-slice (mostly 1 mm) and thick-slice (mostly 5 mm) volumes. Prior arts tend to use 3D approaches for the thin-slice and 2D approaches for the thick-slice, respectively. We aim at a unified approach for both thin- and thick-slice medical volumes. Inspired by recent advances in video analysis, we propose AlignShift, a novel parameter-free operator to convert theoretically any 2D pretrained network into thickness-aware 3D network. Remarkably, the converted networks behave like 3D for the thin-slice, nevertheless degenerate to 2D for the thick-slice adaptively. The unified thickness-aware representation learning is achieved by shifting and fusing aligned “virtual slices” as per the input imaging thickness. Extensive experiments on public large-scale DeepLesion benchmark, consisting of 32 K lesions for universal lesion detection, validate the effectiveness of our method, which outperforms previous state of the art by considerable margins without whistles and bells. More importantly, to our knowledge, this is the first method that bridges the performance gap between thin- and thick-slice volumes by a unified framework. To improve research reproducibility, our code in PyTorch is open source at https://github.com/M3DV/AlignShift." @default.
- W3099683629 created "2020-11-23" @default.
- W3099683629 creator A5014362734 @default.
- W3099683629 creator A5017266884 @default.
- W3099683629 creator A5020501435 @default.
- W3099683629 creator A5042547780 @default.
- W3099683629 creator A5044213341 @default.
- W3099683629 creator A5061294954 @default.
- W3099683629 creator A5087788685 @default.
- W3099683629 date "2020-01-01" @default.
- W3099683629 modified "2023-10-16" @default.
- W3099683629 title "AlignShift: Bridging the Gap of Imaging Thickness in 3D Anisotropic Volumes" @default.
- W3099683629 cites W2119880843 @default.
- W3099683629 cites W2124351162 @default.
- W3099683629 cites W2557738935 @default.
- W3099683629 cites W2565639579 @default.
- W3099683629 cites W2775397671 @default.
- W3099683629 cites W2799913653 @default.
- W3099683629 cites W2810849947 @default.
- W3099683629 cites W2884584803 @default.
- W3099683629 cites W2894585861 @default.
- W3099683629 cites W2912989244 @default.
- W3099683629 cites W2943960805 @default.
- W3099683629 cites W2947413545 @default.
- W3099683629 cites W2952234052 @default.
- W3099683629 cites W2963008565 @default.
- W3099683629 cites W2963150697 @default.
- W3099683629 cites W2963446712 @default.
- W3099683629 cites W2963844898 @default.
- W3099683629 cites W2975885948 @default.
- W3099683629 cites W2979362285 @default.
- W3099683629 cites W2979564444 @default.
- W3099683629 cites W2979708147 @default.
- W3099683629 cites W2979774820 @default.
- W3099683629 cites W2980091915 @default.
- W3099683629 cites W2990152177 @default.
- W3099683629 cites W3026063058 @default.
- W3099683629 cites W3104164805 @default.
- W3099683629 cites W3104211200 @default.
- W3099683629 doi "https://doi.org/10.1007/978-3-030-59719-1_55" @default.
- W3099683629 hasPublicationYear "2020" @default.
- W3099683629 type Work @default.
- W3099683629 sameAs 3099683629 @default.
- W3099683629 citedByCount "13" @default.
- W3099683629 countsByYear W30996836292020 @default.
- W3099683629 countsByYear W30996836292021 @default.
- W3099683629 countsByYear W30996836292022 @default.
- W3099683629 countsByYear W30996836292023 @default.
- W3099683629 crossrefType "book-chapter" @default.
- W3099683629 hasAuthorship W3099683629A5014362734 @default.
- W3099683629 hasAuthorship W3099683629A5017266884 @default.
- W3099683629 hasAuthorship W3099683629A5020501435 @default.
- W3099683629 hasAuthorship W3099683629A5042547780 @default.
- W3099683629 hasAuthorship W3099683629A5044213341 @default.
- W3099683629 hasAuthorship W3099683629A5061294954 @default.
- W3099683629 hasAuthorship W3099683629A5087788685 @default.
- W3099683629 hasBestOaLocation W30996836292 @default.
- W3099683629 hasConcept C11413529 @default.
- W3099683629 hasConcept C13280743 @default.
- W3099683629 hasConcept C154945302 @default.
- W3099683629 hasConcept C160671074 @default.
- W3099683629 hasConcept C174348530 @default.
- W3099683629 hasConcept C185798385 @default.
- W3099683629 hasConcept C192562407 @default.
- W3099683629 hasConcept C205649164 @default.
- W3099683629 hasConcept C31258907 @default.
- W3099683629 hasConcept C41008148 @default.
- W3099683629 hasConcept C49040817 @default.
- W3099683629 hasConceptScore W3099683629C11413529 @default.
- W3099683629 hasConceptScore W3099683629C13280743 @default.
- W3099683629 hasConceptScore W3099683629C154945302 @default.
- W3099683629 hasConceptScore W3099683629C160671074 @default.
- W3099683629 hasConceptScore W3099683629C174348530 @default.
- W3099683629 hasConceptScore W3099683629C185798385 @default.
- W3099683629 hasConceptScore W3099683629C192562407 @default.
- W3099683629 hasConceptScore W3099683629C205649164 @default.
- W3099683629 hasConceptScore W3099683629C31258907 @default.
- W3099683629 hasConceptScore W3099683629C41008148 @default.
- W3099683629 hasConceptScore W3099683629C49040817 @default.
- W3099683629 hasLocation W30996836291 @default.
- W3099683629 hasLocation W30996836292 @default.
- W3099683629 hasLocation W30996836293 @default.
- W3099683629 hasOpenAccess W3099683629 @default.
- W3099683629 hasPrimaryLocation W30996836291 @default.
- W3099683629 hasRelatedWork W118554674 @default.
- W3099683629 hasRelatedWork W2043010663 @default.
- W3099683629 hasRelatedWork W2054685365 @default.
- W3099683629 hasRelatedWork W2120383820 @default.
- W3099683629 hasRelatedWork W2130974462 @default.
- W3099683629 hasRelatedWork W2252959236 @default.
- W3099683629 hasRelatedWork W2272354214 @default.
- W3099683629 hasRelatedWork W2378211422 @default.
- W3099683629 hasRelatedWork W2667588871 @default.
- W3099683629 hasRelatedWork W4321353415 @default.
- W3099683629 isParatext "false" @default.
- W3099683629 isRetracted "false" @default.
- W3099683629 magId "3099683629" @default.
- W3099683629 workType "book-chapter" @default.