Matches in SemOpenAlex for { <https://semopenalex.org/work/W4382203054> ?p ?o ?g. }
- W4382203054 endingPage "450" @default.
- W4382203054 startingPage "441" @default.
- W4382203054 abstract "Background: In the past few years, U-Net based U-shaped architecture and skip-connections have made incredible progress in the field of medical image segmentation. U2-Net achieves good performance in computer vision. However, in the medical image segmentation task, U2-Net with over nesting is easy to overfit. Purpose: A 2D network structure TransU2-Net combining transformer and a lighter weight U2-Net is proposed for automatic segmentation of brain tumor magnetic resonance image (MRI). Methods: The light-weight U2-Net architecture not only obtains multi-scale information but also reduces redundant feature extraction. Meanwhile, the transformer block embedded in the stacked convolutional layer obtains more global information; the transformer with skip-connection enhances spatial domain information representation. A new multi-scale feature map fusion strategy as a postprocessing method was proposed for better fusing high and low-dimensional spatial information. Results: Our proposed model TransU2-Net achieves better segmentation results, on the BraTS2021 dataset, our method achieves an average dice coefficient of 88.17%; Evaluation on the publicly available MSD dataset, we perform tumor evaluation, we achieve a dice coefficient of 74.69%; in addition to comparing the TransU2-Net results are compared with previously proposed 2D segmentation methods. Conclusions: We propose an automatic medical image segmentation method combining transformers and U2-Net, which has good performance and is of clinical importance. The experimental results show that the proposed method outperforms other 2D medical image segmentation methods." @default.
- W4382203054 created "2023-06-28" @default.
- W4382203054 creator A5003843948 @default.
- W4382203054 creator A5004996934 @default.
- W4382203054 creator A5030890710 @default.
- W4382203054 creator A5035530005 @default.
- W4382203054 creator A5053094672 @default.
- W4382203054 creator A5087622241 @default.
- W4382203054 date "2023-01-01" @default.
- W4382203054 modified "2023-10-14" @default.
- W4382203054 title "TransU²-Net: An Effective Medical Image Segmentation Framework Based on Transformer and U²-Net" @default.
- W4382203054 cites W1563697767 @default.
- W4382203054 cites W1641498739 @default.
- W4382203054 cites W1884191083 @default.
- W4382203054 cites W1903029394 @default.
- W4382203054 cites W2085540354 @default.
- W4382203054 cites W2357815549 @default.
- W4382203054 cites W2518599539 @default.
- W4382203054 cites W2558580397 @default.
- W4382203054 cites W2565639579 @default.
- W4382203054 cites W2589409328 @default.
- W4382203054 cites W2751069891 @default.
- W4382203054 cites W2962914239 @default.
- W4382203054 cites W2970546341 @default.
- W4382203054 cites W2996290406 @default.
- W4382203054 cites W3015788359 @default.
- W4382203054 cites W3025800305 @default.
- W4382203054 cites W3091843013 @default.
- W4382203054 cites W3096812112 @default.
- W4382203054 cites W3104258355 @default.
- W4382203054 cites W3170841864 @default.
- W4382203054 cites W3183662711 @default.
- W4382203054 cites W3190096276 @default.
- W4382203054 cites W3203841574 @default.
- W4382203054 cites W3204166336 @default.
- W4382203054 cites W3204255739 @default.
- W4382203054 cites W4214893857 @default.
- W4382203054 doi "https://doi.org/10.1109/jtehm.2023.3289990" @default.
- W4382203054 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37817826" @default.
- W4382203054 hasPublicationYear "2023" @default.
- W4382203054 type Work @default.
- W4382203054 citedByCount "0" @default.
- W4382203054 crossrefType "journal-article" @default.
- W4382203054 hasAuthorship W4382203054A5003843948 @default.
- W4382203054 hasAuthorship W4382203054A5004996934 @default.
- W4382203054 hasAuthorship W4382203054A5030890710 @default.
- W4382203054 hasAuthorship W4382203054A5035530005 @default.
- W4382203054 hasAuthorship W4382203054A5053094672 @default.
- W4382203054 hasAuthorship W4382203054A5087622241 @default.
- W4382203054 hasBestOaLocation W43822030541 @default.
- W4382203054 hasConcept C119599485 @default.
- W4382203054 hasConcept C124504099 @default.
- W4382203054 hasConcept C127413603 @default.
- W4382203054 hasConcept C153180895 @default.
- W4382203054 hasConcept C154945302 @default.
- W4382203054 hasConcept C163892561 @default.
- W4382203054 hasConcept C165801399 @default.
- W4382203054 hasConcept C22019652 @default.
- W4382203054 hasConcept C22029948 @default.
- W4382203054 hasConcept C2524010 @default.
- W4382203054 hasConcept C25694479 @default.
- W4382203054 hasConcept C31972630 @default.
- W4382203054 hasConcept C33923547 @default.
- W4382203054 hasConcept C41008148 @default.
- W4382203054 hasConcept C50644808 @default.
- W4382203054 hasConcept C65885262 @default.
- W4382203054 hasConcept C66322947 @default.
- W4382203054 hasConcept C89600930 @default.
- W4382203054 hasConceptScore W4382203054C119599485 @default.
- W4382203054 hasConceptScore W4382203054C124504099 @default.
- W4382203054 hasConceptScore W4382203054C127413603 @default.
- W4382203054 hasConceptScore W4382203054C153180895 @default.
- W4382203054 hasConceptScore W4382203054C154945302 @default.
- W4382203054 hasConceptScore W4382203054C163892561 @default.
- W4382203054 hasConceptScore W4382203054C165801399 @default.
- W4382203054 hasConceptScore W4382203054C22019652 @default.
- W4382203054 hasConceptScore W4382203054C22029948 @default.
- W4382203054 hasConceptScore W4382203054C2524010 @default.
- W4382203054 hasConceptScore W4382203054C25694479 @default.
- W4382203054 hasConceptScore W4382203054C31972630 @default.
- W4382203054 hasConceptScore W4382203054C33923547 @default.
- W4382203054 hasConceptScore W4382203054C41008148 @default.
- W4382203054 hasConceptScore W4382203054C50644808 @default.
- W4382203054 hasConceptScore W4382203054C65885262 @default.
- W4382203054 hasConceptScore W4382203054C66322947 @default.
- W4382203054 hasConceptScore W4382203054C89600930 @default.
- W4382203054 hasFunder F4320321851 @default.
- W4382203054 hasLocation W43822030541 @default.
- W4382203054 hasLocation W43822030542 @default.
- W4382203054 hasOpenAccess W4382203054 @default.
- W4382203054 hasPrimaryLocation W43822030541 @default.
- W4382203054 hasRelatedWork W2046969815 @default.
- W4382203054 hasRelatedWork W2068271400 @default.
- W4382203054 hasRelatedWork W2185902295 @default.
- W4382203054 hasRelatedWork W2785294226 @default.
- W4382203054 hasRelatedWork W2945274617 @default.
- W4382203054 hasRelatedWork W2973136608 @default.
- W4382203054 hasRelatedWork W3012828488 @default.