Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204000660> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W3204000660 endingPage "525" @default.
- W3204000660 startingPage "515" @default.
- W3204000660 abstract "Accurately segmenting a variety of clinically significant lesions from whole body computed tomography (CT) scans is a critical task on precision oncology imaging, denoted as universal lesion segmentation (ULS). Manual annotation is the current clinical practice, being highly time-consuming and inconsistent on tumor’s longitudinal assessment. Effectively training an automatic segmentation model is desirable but relies heavily on a large number of pixel-wise labelled data. Existing weakly-supervised segmentation approaches often struggle with regions nearby the lesion boundaries. In this paper, we present a novel weakly-supervised universal lesion segmentation method by building an attention enhanced model based on the High-Resolution Network (HRNet), named AHRNet, and propose a regional level set (RLS) loss for optimizing lesion boundary delineation. AHRNet provides advanced high-resolution deep image features by involving a decoder, dual-attention and scale attention mechanisms, which are crucial to performing accurate lesion segmentation. RLS can optimize the model reliably and effectively in a weakly-supervised fashion, forcing the segmentation close to lesion boundary. Extensive experimental results demonstrate that our method achieves the best performance on the publicly large-scale DeepLesion dataset and a hold-out test set." @default.
- W3204000660 created "2021-10-11" @default.
- W3204000660 creator A5014519132 @default.
- W3204000660 creator A5015929533 @default.
- W3204000660 creator A5016038454 @default.
- W3204000660 creator A5022354027 @default.
- W3204000660 creator A5023775139 @default.
- W3204000660 creator A5045227579 @default.
- W3204000660 creator A5051331130 @default.
- W3204000660 creator A5081658414 @default.
- W3204000660 creator A5083081446 @default.
- W3204000660 date "2021-01-01" @default.
- W3204000660 modified "2023-10-05" @default.
- W3204000660 title "Weakly-Supervised Universal Lesion Segmentation with Regional Level Set Loss" @default.
- W3204000660 cites W1884191083 @default.
- W3204000660 cites W1901129140 @default.
- W3204000660 cites W2019607817 @default.
- W3204000660 cites W2108598243 @default.
- W3204000660 cites W2116040950 @default.
- W3204000660 cites W2527671145 @default.
- W3204000660 cites W2560311620 @default.
- W3204000660 cites W2732063980 @default.
- W3204000660 cites W2809942416 @default.
- W3204000660 cites W2810849947 @default.
- W3204000660 cites W2883683269 @default.
- W3204000660 cites W2897666251 @default.
- W3204000660 cites W2899938641 @default.
- W3204000660 cites W2912989244 @default.
- W3204000660 cites W2921110842 @default.
- W3204000660 cites W2921676720 @default.
- W3204000660 cites W2953122916 @default.
- W3204000660 cites W2955058313 @default.
- W3204000660 cites W2963420686 @default.
- W3204000660 cites W2964227007 @default.
- W3204000660 cites W2966702013 @default.
- W3204000660 cites W2979458288 @default.
- W3204000660 cites W3090268382 @default.
- W3204000660 cites W3093193808 @default.
- W3204000660 cites W3094638381 @default.
- W3204000660 cites W3094672651 @default.
- W3204000660 cites W3096907567 @default.
- W3204000660 cites W3108112547 @default.
- W3204000660 cites W3128646645 @default.
- W3204000660 cites W3129517280 @default.
- W3204000660 cites W3011742499 @default.
- W3204000660 doi "https://doi.org/10.1007/978-3-030-87196-3_48" @default.
- W3204000660 hasPublicationYear "2021" @default.
- W3204000660 type Work @default.
- W3204000660 sameAs 3204000660 @default.
- W3204000660 citedByCount "9" @default.
- W3204000660 countsByYear W32040006602021 @default.
- W3204000660 countsByYear W32040006602022 @default.
- W3204000660 countsByYear W32040006602023 @default.
- W3204000660 crossrefType "book-chapter" @default.
- W3204000660 hasAuthorship W3204000660A5014519132 @default.
- W3204000660 hasAuthorship W3204000660A5015929533 @default.
- W3204000660 hasAuthorship W3204000660A5016038454 @default.
- W3204000660 hasAuthorship W3204000660A5022354027 @default.
- W3204000660 hasAuthorship W3204000660A5023775139 @default.
- W3204000660 hasAuthorship W3204000660A5045227579 @default.
- W3204000660 hasAuthorship W3204000660A5051331130 @default.
- W3204000660 hasAuthorship W3204000660A5081658414 @default.
- W3204000660 hasAuthorship W3204000660A5083081446 @default.
- W3204000660 hasBestOaLocation W32040006602 @default.
- W3204000660 hasConcept C153180895 @default.
- W3204000660 hasConcept C154945302 @default.
- W3204000660 hasConcept C177264268 @default.
- W3204000660 hasConcept C199360897 @default.
- W3204000660 hasConcept C31972630 @default.
- W3204000660 hasConcept C41008148 @default.
- W3204000660 hasConcept C89600930 @default.
- W3204000660 hasConceptScore W3204000660C153180895 @default.
- W3204000660 hasConceptScore W3204000660C154945302 @default.
- W3204000660 hasConceptScore W3204000660C177264268 @default.
- W3204000660 hasConceptScore W3204000660C199360897 @default.
- W3204000660 hasConceptScore W3204000660C31972630 @default.
- W3204000660 hasConceptScore W3204000660C41008148 @default.
- W3204000660 hasConceptScore W3204000660C89600930 @default.
- W3204000660 hasLocation W32040006601 @default.
- W3204000660 hasLocation W32040006602 @default.
- W3204000660 hasOpenAccess W3204000660 @default.
- W3204000660 hasPrimaryLocation W32040006601 @default.
- W3204000660 hasRelatedWork W1669643531 @default.
- W3204000660 hasRelatedWork W2005437358 @default.
- W3204000660 hasRelatedWork W2008656436 @default.
- W3204000660 hasRelatedWork W2023558673 @default.
- W3204000660 hasRelatedWork W2039154422 @default.
- W3204000660 hasRelatedWork W2122581818 @default.
- W3204000660 hasRelatedWork W2134924024 @default.
- W3204000660 hasRelatedWork W2517104666 @default.
- W3204000660 hasRelatedWork W2895616727 @default.
- W3204000660 hasRelatedWork W2182382398 @default.
- W3204000660 isParatext "false" @default.
- W3204000660 isRetracted "false" @default.
- W3204000660 magId "3204000660" @default.
- W3204000660 workType "book-chapter" @default.