Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386839517> ?p ?o ?g. }
Showing items 1 to 58 of
58
with 100 items per page.
- W4386839517 abstract "In the current medical image segmentation network, the combination of CNN and Transformer has become a mainstream trend. However, the inherent limitations of convolution operation in CNN and insufficient information interaction in Transformer affect the segmentation performance of the network. To solve these problems, an integrated self-attention and convolution medical image segmentation network (ISC-TransUNet) is proposed in this paper. The network consists of encoder, decoder and jump connection. First, the encoder uses a hybrid structure of BoTNet and Transformer to capture more comprehensive image information and reduce additional computing overhead. Then, the decoder uses an upper sampler cascaded by multiple DUpsampling upper blocks to accurately recover the pixel-level prediction. Finally, the feature fusion of encoder and decoder at different resolutions is realized by ResPath jump connection, which reduces the semantic difference between encoder and decoder. Through experiments on the Synapse multi-organ segmentation dataset, compared with the baseline model TransUNet, Dice similarity coefficient of ISC-TransUNet was improved by 1.13%, Hausdorff distance was reduced by 2.38%, and weight was maintained. The experimental results show that the network can effectively segment tissues and organs in medical images, which has important theoretical significance and application value for intelligent clinical diagnosis and treatment." @default.
- W4386839517 created "2023-09-19" @default.
- W4386839517 creator A5042278439 @default.
- W4386839517 creator A5047916176 @default.
- W4386839517 creator A5061589441 @default.
- W4386839517 creator A5085279585 @default.
- W4386839517 date "2023-10-07" @default.
- W4386839517 modified "2023-10-10" @default.
- W4386839517 title "ISC-Transunet: Medical Image Segmentation Network Based on the Integration of Self-Attention and Convolution" @default.
- W4386839517 cites W2947263797 @default.
- W4386839517 cites W2953129827 @default.
- W4386839517 cites W2962914239 @default.
- W4386839517 cites W2996290406 @default.
- W4386839517 cites W3123982987 @default.
- W4386839517 cites W3204255739 @default.
- W4386839517 doi "https://doi.org/10.1142/s0219519423401073" @default.
- W4386839517 hasPublicationYear "2023" @default.
- W4386839517 type Work @default.
- W4386839517 citedByCount "0" @default.
- W4386839517 crossrefType "journal-article" @default.
- W4386839517 hasAuthorship W4386839517A5042278439 @default.
- W4386839517 hasAuthorship W4386839517A5047916176 @default.
- W4386839517 hasAuthorship W4386839517A5061589441 @default.
- W4386839517 hasAuthorship W4386839517A5085279585 @default.
- W4386839517 hasConcept C111919701 @default.
- W4386839517 hasConcept C118505674 @default.
- W4386839517 hasConcept C124504099 @default.
- W4386839517 hasConcept C153180895 @default.
- W4386839517 hasConcept C154945302 @default.
- W4386839517 hasConcept C160633673 @default.
- W4386839517 hasConcept C31972630 @default.
- W4386839517 hasConcept C41008148 @default.
- W4386839517 hasConcept C89600930 @default.
- W4386839517 hasConceptScore W4386839517C111919701 @default.
- W4386839517 hasConceptScore W4386839517C118505674 @default.
- W4386839517 hasConceptScore W4386839517C124504099 @default.
- W4386839517 hasConceptScore W4386839517C153180895 @default.
- W4386839517 hasConceptScore W4386839517C154945302 @default.
- W4386839517 hasConceptScore W4386839517C160633673 @default.
- W4386839517 hasConceptScore W4386839517C31972630 @default.
- W4386839517 hasConceptScore W4386839517C41008148 @default.
- W4386839517 hasConceptScore W4386839517C89600930 @default.
- W4386839517 hasLocation W43868395171 @default.
- W4386839517 hasOpenAccess W4386839517 @default.
- W4386839517 hasPrimaryLocation W43868395171 @default.
- W4386839517 hasRelatedWork W1522196789 @default.
- W4386839517 hasRelatedWork W1982025852 @default.
- W4386839517 hasRelatedWork W2053596378 @default.
- W4386839517 hasRelatedWork W2085033728 @default.
- W4386839517 hasRelatedWork W2171299904 @default.
- W4386839517 hasRelatedWork W2384362569 @default.
- W4386839517 hasRelatedWork W2922442631 @default.
- W4386839517 hasRelatedWork W4205302943 @default.
- W4386839517 hasRelatedWork W4285411112 @default.
- W4386839517 hasRelatedWork W2181948922 @default.
- W4386839517 isParatext "false" @default.
- W4386839517 isRetracted "false" @default.
- W4386839517 workType "article" @default.