Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386014975> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W4386014975 endingPage "219" @default.
- W4386014975 startingPage "208" @default.
- W4386014975 abstract "Deep learning techniques provide a powerful and versatile tool in different areas, such as object segmentation in medical images. In this paper, we propose a network based on the U-Net architecture to perform the segmentation of wounds and staples in abdominal surgery images. Moreover, since both tasks are highly interdependent, we propose a multitask architecture that allows to simultaneously obtain, in the same network evaluation, the masks with the staples and wound location of the image. When performing this multitasking, it is necessary to formulate a global loss function that linearly combines the losses of both partial tasks. This is why the study also involves the GradNorm algorithm to determine which weight is associated to each loss function during each training step. The main conclusion of the study is that multitask segmentation offers superior performance compared to segmenting by separate tasks." @default.
- W4386014975 created "2023-08-21" @default.
- W4386014975 creator A5038309947 @default.
- W4386014975 creator A5040306427 @default.
- W4386014975 creator A5050863593 @default.
- W4386014975 creator A5073324674 @default.
- W4386014975 date "2023-01-01" @default.
- W4386014975 modified "2023-10-02" @default.
- W4386014975 title "A Multitask Deep Learning Approach for Staples and Wound Segmentation in Abdominal Post-surgical Images" @default.
- W4386014975 cites W1901129140 @default.
- W4386014975 cites W2003245308 @default.
- W4386014975 cites W2738616523 @default.
- W4386014975 cites W2754754109 @default.
- W4386014975 cites W2891675375 @default.
- W4386014975 cites W2976772201 @default.
- W4386014975 cites W2993889133 @default.
- W4386014975 cites W2996242756 @default.
- W4386014975 cites W3005009412 @default.
- W4386014975 cites W3047519784 @default.
- W4386014975 cites W3111142877 @default.
- W4386014975 cites W3119303168 @default.
- W4386014975 cites W3177296395 @default.
- W4386014975 cites W3197657819 @default.
- W4386014975 cites W4205967946 @default.
- W4386014975 cites W4220823596 @default.
- W4386014975 cites W4315648284 @default.
- W4386014975 cites W4316096796 @default.
- W4386014975 doi "https://doi.org/10.1007/978-3-031-39965-7_18" @default.
- W4386014975 hasPublicationYear "2023" @default.
- W4386014975 type Work @default.
- W4386014975 citedByCount "0" @default.
- W4386014975 crossrefType "book-chapter" @default.
- W4386014975 hasAuthorship W4386014975A5038309947 @default.
- W4386014975 hasAuthorship W4386014975A5040306427 @default.
- W4386014975 hasAuthorship W4386014975A5050863593 @default.
- W4386014975 hasAuthorship W4386014975A5073324674 @default.
- W4386014975 hasConcept C107418235 @default.
- W4386014975 hasConcept C108583219 @default.
- W4386014975 hasConcept C119857082 @default.
- W4386014975 hasConcept C124504099 @default.
- W4386014975 hasConcept C14036430 @default.
- W4386014975 hasConcept C154945302 @default.
- W4386014975 hasConcept C15744967 @default.
- W4386014975 hasConcept C180747234 @default.
- W4386014975 hasConcept C31972630 @default.
- W4386014975 hasConcept C41008148 @default.
- W4386014975 hasConcept C78458016 @default.
- W4386014975 hasConcept C86803240 @default.
- W4386014975 hasConcept C89600930 @default.
- W4386014975 hasConceptScore W4386014975C107418235 @default.
- W4386014975 hasConceptScore W4386014975C108583219 @default.
- W4386014975 hasConceptScore W4386014975C119857082 @default.
- W4386014975 hasConceptScore W4386014975C124504099 @default.
- W4386014975 hasConceptScore W4386014975C14036430 @default.
- W4386014975 hasConceptScore W4386014975C154945302 @default.
- W4386014975 hasConceptScore W4386014975C15744967 @default.
- W4386014975 hasConceptScore W4386014975C180747234 @default.
- W4386014975 hasConceptScore W4386014975C31972630 @default.
- W4386014975 hasConceptScore W4386014975C41008148 @default.
- W4386014975 hasConceptScore W4386014975C78458016 @default.
- W4386014975 hasConceptScore W4386014975C86803240 @default.
- W4386014975 hasConceptScore W4386014975C89600930 @default.
- W4386014975 hasLocation W43860149751 @default.
- W4386014975 hasOpenAccess W4386014975 @default.
- W4386014975 hasPrimaryLocation W43860149751 @default.
- W4386014975 hasRelatedWork W1669643531 @default.
- W4386014975 hasRelatedWork W2005437358 @default.
- W4386014975 hasRelatedWork W2008656436 @default.
- W4386014975 hasRelatedWork W2517104666 @default.
- W4386014975 hasRelatedWork W2790662084 @default.
- W4386014975 hasRelatedWork W4223943233 @default.
- W4386014975 hasRelatedWork W4285827401 @default.
- W4386014975 hasRelatedWork W4312200629 @default.
- W4386014975 hasRelatedWork W4360585206 @default.
- W4386014975 hasRelatedWork W4380075502 @default.
- W4386014975 isParatext "false" @default.
- W4386014975 isRetracted "false" @default.
- W4386014975 workType "book-chapter" @default.