Matches in SemOpenAlex for { <https://semopenalex.org/work/W4297338410> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4297338410 abstract "Abstract U-Net has become baseline standard in the medical image segmentation tasks, but it has limitations in explicitly modeling long-term dependencies. Transformer has the ability to capture long-term relevance through its internal self-attention. However, Transformer is committed to modeling the correlation of all elements, but its awareness of local foreground information is not significant. Since medical images are often presented as regional blocks, local information is equally important. In this paper, we propose the GPA-TUNet by considering local and global information synthetically. Specifically, we propose a new attention mechanism to highlight local foreground information, called group parallel axial attention (GPA). Furthermore, we effectively combine GPA with Transformer in encoder part of model. It can not only highlight the foreground information of samples, but also reduce the negative influence of background information on the segmentation results. Meanwhile, we introduced the sMLP block to improve the global modeling capability of network. Sparse connectivity and weight sharing are well achieved by applying it. Extensive experiments on public datasets confirm the excellent performance of our proposed GPA-TUNet. In particular, on Synapse and ACDC datasets, mean DSC(%) reached 80.37% and 90.37% respectively, mean HD95(mm) reached 20.55 and 1.23 respectively." @default.
- W4297338410 created "2022-09-28" @default.
- W4297338410 creator A5040372217 @default.
- W4297338410 creator A5067652312 @default.
- W4297338410 creator A5081489939 @default.
- W4297338410 date "2022-09-27" @default.
- W4297338410 modified "2023-10-16" @default.
- W4297338410 title "Transformer and group parallel axial attention co-encoder for medical image segmentation" @default.
- W4297338410 cites W2395611524 @default.
- W4297338410 cites W2884436604 @default.
- W4297338410 cites W2888358068 @default.
- W4297338410 cites W2962914239 @default.
- W4297338410 cites W2964227007 @default.
- W4297338410 cites W3013198566 @default.
- W4297338410 cites W3017153481 @default.
- W4297338410 cites W3094448207 @default.
- W4297338410 cites W3103010481 @default.
- W4297338410 cites W3193256763 @default.
- W4297338410 cites W3197957534 @default.
- W4297338410 cites W3198141213 @default.
- W4297338410 cites W3212933375 @default.
- W4297338410 cites W4312851276 @default.
- W4297338410 doi "https://doi.org/10.1038/s41598-022-20440-z" @default.
- W4297338410 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36167743" @default.
- W4297338410 hasPublicationYear "2022" @default.
- W4297338410 type Work @default.
- W4297338410 citedByCount "4" @default.
- W4297338410 countsByYear W42973384102023 @default.
- W4297338410 crossrefType "journal-article" @default.
- W4297338410 hasAuthorship W4297338410A5040372217 @default.
- W4297338410 hasAuthorship W4297338410A5067652312 @default.
- W4297338410 hasAuthorship W4297338410A5081489939 @default.
- W4297338410 hasBestOaLocation W42973384101 @default.
- W4297338410 hasConcept C111919701 @default.
- W4297338410 hasConcept C118505674 @default.
- W4297338410 hasConcept C121332964 @default.
- W4297338410 hasConcept C124101348 @default.
- W4297338410 hasConcept C124504099 @default.
- W4297338410 hasConcept C153180895 @default.
- W4297338410 hasConcept C154945302 @default.
- W4297338410 hasConcept C165801399 @default.
- W4297338410 hasConcept C41008148 @default.
- W4297338410 hasConcept C62520636 @default.
- W4297338410 hasConcept C66322947 @default.
- W4297338410 hasConcept C89600930 @default.
- W4297338410 hasConceptScore W4297338410C111919701 @default.
- W4297338410 hasConceptScore W4297338410C118505674 @default.
- W4297338410 hasConceptScore W4297338410C121332964 @default.
- W4297338410 hasConceptScore W4297338410C124101348 @default.
- W4297338410 hasConceptScore W4297338410C124504099 @default.
- W4297338410 hasConceptScore W4297338410C153180895 @default.
- W4297338410 hasConceptScore W4297338410C154945302 @default.
- W4297338410 hasConceptScore W4297338410C165801399 @default.
- W4297338410 hasConceptScore W4297338410C41008148 @default.
- W4297338410 hasConceptScore W4297338410C62520636 @default.
- W4297338410 hasConceptScore W4297338410C66322947 @default.
- W4297338410 hasConceptScore W4297338410C89600930 @default.
- W4297338410 hasIssue "1" @default.
- W4297338410 hasLocation W42973384101 @default.
- W4297338410 hasLocation W42973384102 @default.
- W4297338410 hasLocation W42973384103 @default.
- W4297338410 hasOpenAccess W4297338410 @default.
- W4297338410 hasPrimaryLocation W42973384101 @default.
- W4297338410 hasRelatedWork W134976887 @default.
- W4297338410 hasRelatedWork W1582206143 @default.
- W4297338410 hasRelatedWork W1840273037 @default.
- W4297338410 hasRelatedWork W2138214894 @default.
- W4297338410 hasRelatedWork W2464972745 @default.
- W4297338410 hasRelatedWork W2549765251 @default.
- W4297338410 hasRelatedWork W2734888972 @default.
- W4297338410 hasRelatedWork W3027394838 @default.
- W4297338410 hasRelatedWork W3161321444 @default.
- W4297338410 hasRelatedWork W4376624981 @default.
- W4297338410 hasVolume "12" @default.
- W4297338410 isParatext "false" @default.
- W4297338410 isRetracted "false" @default.
- W4297338410 workType "article" @default.